US 11,568,136 B2Grant
Automatically constructing lexicons from unlabeled datasets
Issue Date:2023-01-31
•20 Claims
•20 Drawing Sheets
Abstract
A system, method, and computer-readable medium are disclosed for performing a lexicon construction operation. The lexicon construction operation includes: identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term; grouping terms from the plurality of training events into topic clusters; analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters; and, deriving a plurality of learned lexicons from the plurality of classified clusters.
Metadata
Assignee
- Forcepoint LLC
Inventors
- Christopher Poirel
- Amanda Kinnischtzke
Application Information
Application Number:US 16/849,615
Filing Date:2020-04-15
Priority Date:2020-04-15
Art Unit:2677
Classifications
IPC:
G06F40/237G06N20/00G10L15/18G06F21/31G06F21/55
Field of Search:
G06F 40/237G06F 21/31G06F 21/55G06N 20/00G10L 15/18
Patent Drawings (20 sheets)
Description
BACKGROUND OF THE INVENTION
Field of the Invention
[0001] The present invention relates in general to the field of computers and similar technologies, and in particular to software utilized in this field. Still more particularly, it relates to a method, system and computer-usable medium for constructing a lexicon for use in detecting entity behavior of analytic utility.
Description of the Related Art
[0002] Users interact with physical, system, data, and services resources of all kinds, as well as each other, on a daily basis. Each of these interactions, whether accidental or intended, poses some degree of security risk. However, not all behavior poses the same risk. Furthermore, determining the extent of risk corresponding to individual events can be difficult. In particular, ensuring that an entity is who they claim to be can be challenging.
[0003] As an example, a first user may attempt to pose as a second user to gain access to certain confidential information. In this example, the first user may be prevented from accessing the confidential information if it can be determined that they are illegitimately posing as the second user. More particularly, access to the confidential information may be prevented if the identity of the first user is resolved prior to the confidential information actually being accessed. Likewise, the first user's access to the confidential information may be prevented if their identity cannot be resolved to the identity of the second user.
SUMMARY OF THE INVENTION
[0004] In one embodiment the invention relates to a method for construction a lexicon comprising: identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term; grouping terms from the plurality of training events into topic clusters; analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters; and, deriving a plurality of learned lexicons from the plurality of classified clusters.
[0005] In another embodiment the invention relates to a system comprising: a processor; a data bus coupled to the processor; and a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for: identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term; grouping terms from the plurality of training events into topic clusters; analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters; and, deriving a plurality of learned lexicons from the plurality of classified clusters.
[0006] In another embodiment the invention relates to a computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for: identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term; grouping terms from the plurality of training events into topic clusters; analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters; and, deriving a plurality of learned lexicons from the plurality of classified clusters.
BRIEF DESCRIPTION OF THE DRAWINGS
[0007] The present invention may be better understood, and its numerous objects, features and advantages made apparent to those skilled in the art by referencing the accompanying drawings. The use of the same reference number throughout the several figures designates a like or similar element.
[0008] FIG. 1 depicts an exemplary client computer in which the present invention may be implemented;
[0009] FIG. 2 is a simplified block diagram of an edge device;
[0010] FIG. 3 is a simplified block diagram of an endpoint agent;
[0011] FIG. 4 is a simplified block diagram of a security analytics system;
[0012] FIG. 5 is a simplified block diagram of the operation of a security analytics system;
[0013] FIG. 6 shows a simplified block diagram of an entity behavior profile (EBP);
[0014] FIGS. 7a and 7b are a simplified block diagram of the operation of a security analytics system;
[0015] FIG. 8 is a simplified block diagram showing the mapping of an event to a security vulnerability scenario;
[0016] FIG. 9 is a simplified block diagram of the generation of a session and a corresponding session-based fingerprint;
[0017] FIG. 10 is a generalized flowchart of the performance of session fingerprint generation operations;
[0018] FIG. 11 is simplified block diagram of process flows associated with the operation of an entity behavior catalog (EBC) system;
[0019] FIG. 12 is a simplified block diagram of process flows associated with constructing a lexicon for use in detecting entity behavior of analytic utility;
[0020] FIG. 13 is a table showing components of an EBP;
[0021] FIG. 14 is a activities table showing analytic utility actions occurring during a session;
[0022] FIGS. 15a and 15b are a generalized flowchart of the performance of EBC operations;
[0023] FIG. 16 shows a functional block diagram of the operation of an EBC system;
[0024] FIGS. 17a and 17b are a simplified block diagram showing reference architecture components of an EBC system;
[0025] FIG. 18 is a simplified block diagram showing the mapping of entity behaviors to a risk use case scenario; and
[0026] FIG. 19 is a simplified block diagram of an EBC system environment.
DETAILED DESCRIPTION
[0027] A method, system and computer-usable medium are disclosed for constructing a lexicon for use in detecting entity behavior of analytic utility. Certain aspects of the invention reflect an appreciation that the existence of any entity, whether it is an individual user, a group of users, an organization, a device, a system, a network, an account, a domain, an operation, a process, a software application, or a service, represents some degree of security risk. Certain aspects of the invention likewise reflect an appreciation that observation of an entity's behavior can often provide an indication of possible anomalous, abnormal, unexpected, or malicious behavior, any or all of which may represent a security risk.
[0028] Certain aspects of the invention reflect an appreciation that an entity's behavior can be thought of as discrete events, described in greater detail herein, involving either themselves, one or more other entities, or a combination thereof. Likewise, certain aspects of the invention reflect an appreciation that information associated with such events, herein referred to as event information, often includes certain terms that may be related to anomalous, abnormal, unexpected, or malicious entity behavior. However, certain aspects of the invention likewise reflect an appreciation that lexicons used to identify such terms may not contain all terms related to a particular entity behavior, especially if it is considered anomalous, abnormal, unexpected, or malicious. Certain aspects of the invention reflect an appreciation that current approaches to adding additional relevant terms to a particular lexicon often involve manual processes, which can be cumbersome, time consuming, and error-prone. Accordingly, certain aspects of the invention likewise reflect an appreciation that automating the addition of relevant terms to a particular lexicon may not only be more efficient, take less time, and reduce potential errors, but may also assist in identifying anomalous, abnormal, unexpected, or malicious entity behavior.
[0029] Various aspects of the invention likewise reflect an appreciation that certain non-user entities, such as computing, communication, and surveillance devices can be a source for telemetry associated with certain events and entity behaviors. Likewise, various aspects of the invention reflect an appreciation that certain accounts may be global, spanning multiple devices, such as a domain-level account allowing an entity access to multiple systems. Certain aspects of the invention likewise reflect an appreciation that a particular account may be shared by multiple entities.
[0030] Accordingly, certain aspects of the invention reflect an appreciation that a particular entity can be assigned a measure of risk according to its respective attributes, behaviors, associated behavioral models, and resultant inferences contained in an associated profile. As an example, a first profile may have an attribute that its corresponding entity works in the human resource department, while a second profile may have an attribute that its corresponding entity is an email server. To continue the example, the first profile may have an associated behavior that indicates its corresponding entity is not acting as they did the day before, while the second profile may have an associated behavior that indicates its corresponding entity is connecting to a suspicious IP address. To further continue the example, the first profile may have a resultant inference that its corresponding entity is likely to be leaving the company, while the second profile may have a resultant inference that there is a high probability its corresponding entity is compromised. Accordingly, certain aspects of the invention reflect an appreciation that a catalog of such behaviors, and associated profiles, can assist in identifying entity behavior that may be of analytic utility. Likewise, certain aspects of the invention reflect an appreciation that such entity behavior of analytic utility may be determined to be anomalous, abnormal, unexpected, malicious, or some combination thereof, as described in greater detail herein.
[0031] For the purposes of this disclosure, computer-readable media may include any instrumentality or aggregation of instrumentalities that may retain data and/or instructions for a period of time. Computer-readable media may include, without limitation, storage media such as a direct access storage device (e.g., a hard disk drive or solid state drive), a sequential access storage device (e.g., a tape disk drive), optical storage device, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and/or flash memory; as well as communications media such as wires, optical fibers, microwaves, radio waves, and other electromagnetic and/or optical carriers; and/or any combination of the foregoing.
[0032] FIG. 1 is a generalized illustration of an information handling system 100 that can be used to implement the system and method of the present invention. The information handling system 100 includes a processor (e.g., central processor unit or “CPU”) 102, input/output (I/O) devices 104, such as a display, a keyboard, a mouse, and associated controllers, a storage system 106, and various other subsystems 108. In various embodiments, the information handling system 100 also includes network port 110 operable to connect to a network 140, which is likewise accessible by a service provider server 142. The information handling system 100 likewise includes system memory 112, which is interconnected to the foregoing via one or more buses 114. System memory 112 further includes operating system (OS) 116 and in certain embodiments may also include a security analytics system 118, or a lexicon construction system 124, or both. In certain embodiments, the information handling system 100 may be implemented to download the security analytics system 118, or the lexicon construction system 124, or both, from the service provider server 142. In certain embodiments, the security analytics system 118, or the lexicon construction system 124, or both, may be provided as a service from the service provider server 142.
[0033] In various embodiments, the security analytics system 118 may be implemented to perform a security analytics operation. In certain embodiments, the security analytics operation improves processor efficiency, and thus the efficiency of the information handling system 100, by facilitating security analytics functions. As will be appreciated, once the information handling system 100 is configured to perform the security analytics operation, the information handling system 100 becomes a specialized computing device specifically configured to perform the security analytics operation and is not a general purpose computing device. Moreover, the implementation of the security analytics system 118 on the information handling system 100 improves the functionality of the information handling system 100 and provides a useful and concrete result of performing security analytics functions to mitigate security risk.
[0034] In certain embodiments, the security analytics system 118 may be implemented to include an entity behavior catalog (EBC) system 120, an entity behavior detection system 122, or both. In certain embodiments, the EBC system 120 may be implemented to catalog entity behavior, as described in greater detail herein. In various embodiments, the lexicon construction system 124 may be implemented to process certain features associated with one or more events, as likewise described in greater detail herein, to construct a lexicon. In various embodiments, the entity behavior detection system 122 may be implemented to use a lexicon constructed by the lexicon construction system 12 to perform certain entity behavior detection operations, as described in greater detail herein.
[0035] FIG. 2 is a simplified block diagram of an edge device implemented in accordance with an embodiment of the invention. As used herein, an edge device, such as the edge device 202 shown in FIG. 2 , broadly refers to a device providing an entry point into a network 140. Examples of such edge devices 202 may include routers, routing switches, integrated access devices (IADs), multiplexers, wide-area network (WAN) access devices, and network security appliances. In certain embodiments, the network 140 may be a private network (e.g., an enterprise network), a semi-public network (e.g., a service provider core network), or a public network (e.g., the Internet).
[0036] Skilled practitioners of the art will be aware that edge devices 202 are often implemented as routers that provide authenticated access to faster, more efficient backbone and core networks. Furthermore, current industry trends include making edge devices 202 more intelligent, which allows core devices to operate at higher speed as they are not burdened with additional administrative overhead. Accordingly, such edge devices 202 often include Quality of Service (QoS) and multi-service functions to manage different types of traffic. Consequently, it is common to design core networks with switches that use routing protocols such as Open Shortest Path First (OSPF) or Multiprotocol Label Switching (MPLS) for reliability and scalability. Such approaches allow edge devices 202 to have redundant links to the core network, which not only provides improved reliability, but enables enhanced, flexible, and scalable security capabilities as well.
[0037] In certain embodiments, the edge device 202 may be implemented to include a communications/services architecture 204, various pluggable capabilities 212, a traffic router 210, and a pluggable hosting framework 208. In certain embodiments, the communications/services architecture 202 may be implemented to provide access to and from various networks 140, cloud services 206, or a combination thereof. In certain embodiments, the cloud services 206 may be provided by a cloud infrastructure familiar to those of skill in the art. In certain embodiments, the edge device 202 may be implemented to provide support for a variety of generic services, such as directory integration, logging interfaces, update services, and bidirectional risk/context flows associated with various analytics. In certain embodiments, the edge device 202 may be implemented to provide temporal information, described in greater detail herein, associated with the provision of such services.
[0038] In certain embodiments, the edge device 202 may be implemented as a generic device configured to host various network communications, data processing, and security management capabilities. In certain embodiments, the pluggable hosting framework 208 may be implemented to host such capabilities in the form of pluggable capabilities 212. In certain embodiments, the pluggable capabilities 212 may include capability ‘1’ 214 (e.g., basic firewall), capability ‘2’ 216 (e.g., general web protection), capability ‘3’ 218 (e.g., data sanitization), and so forth through capability ‘n’ 220, which may include capabilities needed for a particular operation, process, or requirement on an as-needed basis. In certain embodiments, such capabilities may include the performance of operations associated with providing real-time resolution of the identity of an entity at a particular point in time. In certain embodiments, such operations may include the provision of associated temporal information (e.g., time stamps).
[0039] In certain embodiments, the pluggable capabilities 212 may be sourced from various cloud services 206. In certain embodiments, the pluggable hosting framework 208 may be implemented to provide certain computing and communication infrastructure components, and foundation capabilities, required by one or more of the pluggable capabilities 212. In certain embodiments, the pluggable hosting framework 208 may be implemented to allow the pluggable capabilities 212 to be dynamically invoked. Skilled practitioners of the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0040] FIG. 3 is a simplified block diagram of an endpoint agent implemented in accordance with an embodiment of the invention. As used herein, an endpoint agent 306 broadly refers to a software agent used in combination with an endpoint device 304 to establish a protected endpoint 302. Skilled practitioners of the art will be familiar with software agents, which are computer programs that perform actions on behalf of a user or another program. In various approaches, a software agent may be autonomous or work together with another agent or a user. In certain of these approaches the software agent is implemented to autonomously decide if a particular action is appropriate for a given event, such as an observed entity behavior, described in greater detail herein.
[0041] An endpoint device 304, as likewise used herein, refers to an information processing system such as a personal computer, a laptop computer, a tablet computer, a personal digital assistant (PDA), a smart phone, a mobile telephone, a digital camera, a video camera, or other device that is capable of storing, processing and communicating data. In certain embodiments, the communication of the data may take place in real-time or near-real-time. As used herein, real-time broadly refers to processing and providing information within a time interval brief enough to not be discernable by a user. As an example, a cellular phone conversation may be used to communicate information in real-time, while an instant message (IM) exchange may be used to communicate information in near real-time. In certain embodiments, the communication of the information may take place asynchronously. For example, an email message may be stored on an endpoint device 304 when it is offline. In this example, the information may be communicated to its intended recipient once the endpoint device 304 gains access to a network 140.
[0042] A protected endpoint 302, as likewise used herein, broadly refers to a policy-based approach to network security that typically requires endpoint devices 304 to comply with particular criteria before they are granted access to network resources. As an example, a given endpoint device 304 may be required to have a particular operating system (OS), or version thereof, a Virtual Private Network (VPN) client, anti-virus software with current updates, and so forth. In certain embodiments, the protected endpoint 302 may be implemented to perform operations associated with providing real-time resolution of the identity of an entity at a particular point in time, as described in greater detail herein. In certain embodiments, the protected endpoint 302 may be implemented to provide temporal information, such as timestamp information, associated with such operations.
[0043] In certain embodiments, the real-time resolution of the identity of an entity at a particular point in time may be based upon contextual information associated with a given entity behavior. As used herein, contextual information broadly refers to any information, directly or indirectly, individually or in combination, related to a particular entity behavior. In certain embodiments, entity behavior may include an entity's physical behavior, cyber behavior, or a combination thereof. As likewise used herein, physical behavior broadly refers to any entity behavior occurring within a physical realm. More particularly, physical behavior may include any action enacted by an entity that can be objectively observed, or indirectly inferred, within a physical realm.
[0044] As an example, a user may attempt to use an electronic access card to enter a secured building at a certain time. In this example, the use of the access card to enter the building is the action and the reading of the access card makes the user's physical behavior electronically-observable. As another example, a first user may physically transfer a document to a second user, which is captured by a video surveillance system. In this example, the physical transferal of the document from the first user to the second user is the action. Likewise, the video record of the transferal makes the first and second user's physical behavior electronically-observable. As used herein, electronically-observable user behavior broadly refers to any behavior exhibited or enacted by a user that can be electronically observed.
[0045] Cyber behavior, as used herein, broadly refers to any behavior occurring in cyberspace, whether enacted by an individual user, a group of users, or a system acting at the behest of an individual user, a group of users, or an entity. More particularly, cyber behavior may include physical, social, or mental actions that can be objectively observed, or indirectly inferred, within cyberspace. As an example, a user may use an endpoint device 304 to access and browse a particular website on the Internet. In this example, the individual actions performed by the user to access and browse the website constitute a cyber behavior. As another example, a user may use an endpoint device 304 to download a data file from a particular system at a particular point in time. In this example, the individual actions performed by the user to download the data file, and associated temporal information, such as a time-stamp associated with the download, constitute a cyber behavior. In these examples, the actions are enacted within cyberspace, in combination with associated temporal information, makes them electronically-observable.
[0046] As likewise used herein, cyberspace broadly refers to a network 140 environment capable of supporting communication between two or more entities. In certain embodiments, the entity may be a user, an endpoint device 304, or various resources, described in greater detail herein. In certain embodiments, the entities may include various endpoint devices 304 or resources operating at the behest of an entity, such as a user. In certain embodiments, the communication between the entities may include audio, image, video, text, or binary data.
[0047] As described in greater detail herein, the contextual information may include an entity's authentication factors. Contextual information may likewise include various temporal identity resolution factors, such as identification factors associated with the entity, the date/time/frequency of various entity behaviors, the entity's location, the entity's role or position in an organization, their associated access rights, and certain user gestures employed by the user in the enactment of a user behavior. Other contextual information may likewise include various user interactions, whether the interactions are with an endpoint device 304, a network 140, a resource, or another user. In certain embodiments, user behaviors, and their related contextual information, may be collected at particular points of observation, and at particular points in time, described in greater detail herein. In certain embodiments, a protected endpoint 302 may be implemented as a point of observation for the collection of entity behavior and contextual information.
[0048] In certain embodiments, the endpoint agent 306 may be implemented to universally support a variety of operating systems, such as Apple Macintosh®, Microsoft Windows®, Linux®, Android® and so forth. In certain embodiments, the endpoint agent 306 may be implemented to interact with the endpoint device 304 through the use of low-level hooks 312 at the operating system level. It will be appreciated that the use of low-level hooks 312 allows the endpoint agent 306 to subscribe to multiple events through a single hook. Consequently, multiple functionalities provided by the endpoint agent 306 can share a single data stream, using only those portions of the data stream they may individually need. Accordingly, system efficiency can be improved and operational overhead reduced.
[0049] In certain embodiments, the endpoint agent 306 may be implemented to provide a common infrastructure for pluggable feature packs 308. In various embodiments, the pluggable feature packs 308 may provide certain security management functionalities. Examples of such functionalities may include various anti-virus and malware detection, data loss protection (DLP), insider threat detection, and so forth. In certain embodiments, the security management functionalities may include one or more functionalities associated with providing real-time resolution of the identity of an entity at a particular point in time, as described in greater detail herein.
[0050] In certain embodiments, a particular pluggable feature pack 308 may be invoked as needed by the endpoint agent 306 to provide a given functionality. In certain embodiments, individual features of a particular pluggable feature pack 308 are invoked as needed. It will be appreciated that the ability to invoke individual features of a pluggable feature pack 308, without necessarily invoking all such features, will likely improve the operational efficiency of the endpoint agent 306 while simultaneously reducing operational overhead. Accordingly, the endpoint agent 306 can self-optimize in certain embodiments by using the common infrastructure and invoking only those pluggable components that are applicable or needed for a given user behavior.
[0051] In certain embodiments, the individual features of a pluggable feature pack 308 are invoked by the endpoint agent 306 according to the occurrence of a particular user behavior. In certain embodiments, the individual features of a pluggable feature pack 308 are invoked by the endpoint agent 306 according to the occurrence of a particular temporal event, described in greater detail herein. In certain embodiments, the individual features of a pluggable feature pack 308 are invoked by the endpoint agent 306 at a particular point in time. In these embodiments, the method by which a given user behavior, temporal event, or point in time is selected is a matter of design choice.
[0052] In certain embodiments, the individual features of a pluggable feature pack 308 may be invoked by the endpoint agent 306 according to the context of a particular user behavior. As an example, the context may be the user enacting the user behavior, their associated risk classification, which resource they may be requesting, the point in time the user behavior is enacted, and so forth. In certain embodiments, the pluggable feature packs 308 may be sourced from various cloud services 206. In certain embodiments, the pluggable feature packs 308 may be dynamically sourced from various cloud services 206 by the endpoint agent 306 on an as-needed basis.
[0053] In certain embodiments, the endpoint agent 306 may be implemented with additional functionalities, such as event analytics 310. In certain embodiments, the event analytics 310 functionality may include analysis of various user behaviors, described in greater detail herein. In certain embodiments, the endpoint agent 306 may be implemented with a thin hypervisor 314, which can be run at Ring −1, thereby providing protection for the endpoint agent 306 in the event of a breach. As used herein, a thin hypervisor broadly refers to a simplified, OS-dependent hypervisor implemented to increase security. As likewise used herein, Ring −1 broadly refers to approaches allowing guest operating systems to run Ring 0 (i.e., kernel) operations without affecting other guests or the host OS. Those of skill in the art will recognize that many such embodiments and examples are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0054] FIG. 4 is a simplified block diagram of a security analytics system implemented in accordance with an embodiment of the invention. In certain embodiments, the security analytics system 118 shown in FIG. 4 may include an event queue analytics 404 module, described in greater detail herein. In certain embodiments, the event queue analytics 404 sub-system may be implemented to include an enrichment 406 module and a streaming analytics 408 module. In certain embodiments, the security analytics system 118 may be implemented to provide log storage, reporting, and analytics capable of performing streaming 408 and on-demand 410 analytics operations. In certain embodiments, such operations may be associated with defining and managing an entity behavior profile (EBP), described in greater detail herein. In certain embodiments, an EBP may be implemented as an adaptive trust profile (ATP). In certain embodiments, an EBP may be implemented to detect entity behavior that may be of analytic utility, adaptively responding to mitigate risk, or a combination thereof, as described in greater detail herein. In certain embodiments, entity behavior of analytic utility may be determined to be anomalous, abnormal, unexpected, malicious, or some combination thereof, as likewise described in greater detail herein.
[0055] In certain embodiments, the security analytics system 118 may be implemented to provide a uniform platform for storing events and contextual information associated with various entity behaviors and performing longitudinal analytics. As used herein, longitudinal analytics broadly refers to performing analytics of entity behaviors occurring over a particular period of time. As an example, an entity may iteratively attempt to access certain proprietary information stored in various locations. In addition, the attempts may occur over a brief period of time. To continue the example, the fact that the information the user is attempting to access is proprietary, that it is stored in various locations, and the attempts are occurring in a brief period of time, in combination, may indicate the entity behavior enacted by the entity is suspicious. As another example, certain entity identifier information (e.g., a user name) associated with an entity may change over time. In this example, a change in the entity's user name, during a particular time period or at a particular point in time, may represent suspicious entity behavior.
[0056] In certain embodiments, the security analytics system 118 may be implemented to be scalable. In certain embodiments, the security analytics system 118 may be implemented in a centralized location, such as a corporate data center. In these embodiments, additional resources may be added to the security analytics system 118 as needs grow. In certain embodiments, the security analytics system 118 may be implemented as a distributed system. In these embodiments, the security analytics system 118 may span multiple information handling systems. In certain embodiments, the security analytics system 118 may be implemented in a cloud environment. In certain embodiments, the security analytics system 118 may be implemented in a virtual machine (VM) environment. In such embodiments, the VM environment may be configured to dynamically and seamlessly scale the security analytics system 118 as needed. Skilled practitioners of the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0057] In certain embodiments, an event stream collector 402 may be implemented to collect event and related contextual information, described in greater detail herein, associated with various entity behaviors. In these embodiments, the method by which the event and contextual information is selected to be collected by the event stream collector 402 is a matter of design choice. In certain embodiments, the event and contextual information collected by the event stream collector 402 may be processed by an enrichment module 406 to generate enriched entity behavior information. In certain embodiments, the enrichment may include certain contextual information related to a particular entity behavior or event. In certain embodiments, the enrichment may include certain temporal information, such as timestamp information, related to a particular entity behavior or event.
[0058] In certain embodiments, enriched entity behavior information may be provided by the enrichment module 406 to a streaming 408 analytics module. In turn, the streaming 408 analytics module may provide some or all of the enriched entity behavior information to an on-demand 410 analytics module. As used herein, streaming 408 analytics broadly refers to analytics performed in near real-time on enriched entity behavior information as it is received. Likewise, on-demand 410 analytics broadly refers herein to analytics performed, as they are requested, on enriched entity behavior information after it has been received. In certain embodiments, the enriched entity behavior information may be associated with a particular event. In certain embodiments, the enrichment 406 and streaming analytics 408 modules may be implemented to perform event queue analytics 404 operations, as described in greater detail herein.
[0059] In certain embodiments, the on-demand 410 analytics may be performed on enriched entity behavior associated with a particular interval of, or point in, time. In certain embodiments, the streaming 408 or on-demand 410 analytics may be performed on enriched entity behavior associated with a particular user, group of users, one or more non-user entities, or a combination thereof. In certain embodiments, the streaming 408 or on-demand 410 analytics may be performed on enriched entity behavior associated with a particular resource, such as a facility, system, datastore, or service. Those of skill in the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0060] In certain embodiments, the results of various analytics operations performed by the streaming 408 or on-demand 410 analytics modules may be provided to a storage Application Program Interface (API) 414. In turn, the storage API 412 may be implemented to provide access to various datastores ‘1’ 416 through ‘n’ 418, which in turn are used to store the results of the analytics operations. In certain embodiments, the security analytics system 118 may be implemented with a logging and reporting front-end 412, which is used to receive the results of analytics operations performed by the streaming 408 analytics module. In certain embodiments, the datastores ‘1’ 416 through ‘n’ 418 may variously include a datastore of entity identifiers, temporal events, or a combination thereof.
[0061] In certain embodiments, the security analytics system 118 may include a risk scoring 420 module implemented to perform risk scoring operations, described in greater detail herein. In certain embodiments, functionalities of the risk scoring 420 module may be provided in the form of a risk management service 422. In certain embodiments, the risk management service 422 may be implemented to perform operations associated with defining and managing an entity behavior profile (EBP), as described in greater detail herein. In certain embodiments, the risk management service 422 may be implemented to perform operations associated with detecting entity behavior that may be of analytic utility and adaptively responding to mitigate risk, as described in greater detail herein. In certain embodiments, the risk management service 422 may be implemented to provide the results of various analytics operations performed by the streaming 406 or on-demand 408 analytics modules. In certain embodiments, the risk management service 422 may be implemented to use the storage API 412 to access various enhanced cyber behavior and analytics information stored on the datastores ‘1’ 414 through ‘n’ 416. Skilled practitioners of the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0062] FIG. 5 is a simplified block diagram of the operation of a security analytics system implemented in accordance with an embodiment of the invention. In certain embodiments, the security analytics system 118 may be implemented to perform operations associated with providing real-time resolution of the identity of an entity at a particular point in time. In certain embodiments, the security analytics system 118 may be implemented in combination with one or more endpoint agents 306, one or more edge devices 202, cloud services 206, and a security analytics system 118, and a network 140 to perform such operations.
[0063] In certain embodiments, the network edge device 202 may be implemented in a bridge, a firewall, or a passive monitoring configuration. In certain embodiments, the edge device 202 may be implemented as software running on an information processing system. In certain embodiments, the network edge device 202 may be implemented to provide integrated logging, updating and control. In certain embodiments, the edge device 202 may be implemented to receive network requests and context-sensitive cyber behavior information in the form of enriched cyber behavior information 510, described in greater detail herein, from an endpoint agent 306, likewise described in greater detail herein.
[0064] In certain embodiments, the security analytics system 118 may be implemented as both a source and a sink of entity behavior information. In certain embodiments, the security analytics system 118 may be implemented to serve requests for user/resource risk data. In certain embodiments, the edge device 202 and the endpoint agent 306, individually or in combination, may provide certain entity behavior information to the security analytics system 118 using either push or pull approaches familiar to skilled practitioners of the art.
[0065] As described in greater detail herein, the edge device 202 may be implemented in certain embodiments to receive enriched user behavior information 510 from the endpoint agent 306. It will be appreciated that such enriched user behavior information 510 will likely not be available for provision to the edge device 202 when an endpoint agent 306 is not implemented for a corresponding endpoint device 304. However, the lack of such enriched user behavior information 510 may be accommodated in various embodiments, albeit with reduced functionality associated with operations associated with providing real-time resolution of the identity of an entity at a particular point in time.
[0066] In certain embodiments, a given user behavior may be enriched by an associated endpoint agent 306 attaching contextual information to a request. In one embodiment, the context is embedded within a network request, which is then provided as enriched user behavior information 510. In another embodiment, the contextual information is concatenated, or appended, to a request, which in turn is provided as enriched user behavior information 510. In these embodiments, the enriched user behavior information 510 is unpacked upon receipt and parsed to separate the request and its associated contextual information. Those of skill in the art will recognize that one possible disadvantage of such an approach is that it may perturb certain Intrusion Detection System and/or Intrusion Detection Prevention (IDS/IDP) systems implemented on a network 140.
[0067] In certain embodiments, new flow requests are accompanied by a contextual information packet sent to the edge device 202. In these embodiments, the new flow requests may be provided as enriched user behavior information 510. In certain embodiments, the endpoint agent 306 may also send updated contextual information to the edge device 202 once it becomes available. As an example, an endpoint agent 306 may share a list of files that have been read by a current process at any point in time once the information has been collected. To continue the example, such a list of files may be used to determine which data the endpoint agent 306 may be attempting to exfiltrate.
[0068] In certain embodiments, point analytics processes executing on the edge device 202 may request a particular service. As an example, risk scores on a per-user basis may be requested. In certain embodiments, the service may be requested from the security analytics system 118. In certain embodiments, the service may be requested from various cloud services 206.
[0069] In certain embodiments, contextual information associated with a user behavior may be attached to various network service requests. In certain embodiments, the request may be wrapped and then handled by proxy. In certain embodiments, a small packet of contextual information associated with a user behavior may be sent with a service request. In certain embodiments, service requests may be related to Domain Name Service (DNS), web, email, and so forth, all of which are essentially requests for service by an endpoint device 304. In certain embodiments, such service requests may be associated with temporal event information, described in greater detail herein. Consequently, such requests can be enriched by the addition of user behavior contextual information (e.g., UserAccount, interactive/automated, data-touched, temporal event information, etc.). Accordingly, the edge device 202 can then use this information to manage the appropriate response to submitted requests. In certain embodiments, such requests may be associated with providing real-time resolution of the identity of an entity at a particular point in time.
[0070] In certain embodiments, the security analytics system 118 may be implemented in different operational configurations. In one embodiment, the security analytics system 118 may be implemented by using the endpoint agent 306. In another embodiment, the security analytics system 118 may be implemented by using endpoint agent 306 in combination with the edge device 202. In certain embodiments, the cloud services 206 may likewise be implemented for use by the endpoint agent 306, the edge device 202, and the security analytics system 118, individually or in combination. In these embodiments, the security analytics system 118 may be primarily oriented to performing risk assessment operations related to user actions, program actions, data accesses, or a combination thereof. In certain embodiments, program actions may be treated as a proxy for the user.
[0071] In certain embodiments, the endpoint agent 306 may be implemented to update the security analytics system 118 with user behavior and associated contextual information, thereby allowing an offload of certain analytics processing overhead. In one embodiment, this approach allows for longitudinal risk scoring, which assesses risk associated with certain user behavior during a particular interval of time. In another embodiment, the security analytics system 118 may be implemented to perform risk-adaptive operations to access risk scores associated with the same user account, but accrued on different endpoint devices 304. It will be appreciated that such an approach may prove advantageous when an adversary is “moving sideways” through a network environment, using different endpoint devices 304 to collect information.
[0072] In certain embodiments, the security analytics system 118 may be primarily oriented to applying risk mitigations in a way that maximizes security effort return-on-investment (ROI). In certain embodiments, the approach may be accomplished by providing additional contextual and user behavior information associated with user requests. As an example, a web gateway may not concern itself with why a particular file is being requested by a certain entity at a particular point in time. Accordingly, if the file cannot be identified as malicious or harmless, there is no context available to determine how, or if, to proceed.
[0073] To extend the example, the edge device 202 and security analytics system 118 may be coupled such that requests can be contextualized and fitted into a framework that evaluates their associated risk. It will be appreciated that such an embodiment works well with web-based data loss protection (DLP) approaches, as each transfer is no longer examined in isolation, but in the broader context of an identified user's actions, at a particular time, on the network 140.
[0074] As another example, the security analytics system 118 may be implemented to perform risk scoring processes to decide whether to block or allow unusual flows. It will be appreciated that such an approach is highly applicable to defending against point-of-sale (POS) malware, a breach technique that has become increasingly more common in recent years. It will likewise be appreciated that while various edge device 202 implementations may not stop all such exfiltrations, they may be able to complicate the task for the attacker.
[0075] In certain embodiments, the security analytics system 118 may be primarily oriented to maximally leverage contextual information associated with various user behaviors within the system. In certain embodiments, data flow tracking is performed by one or more endpoint agents 306, which allows the quantity and type of information associated with particular hosts to be measured. In turn, this information may be used to determine how the edge device 202 handles requests. By contextualizing such user behavior on the network 140, the security analytics system 118 can provide intelligent protection, making decisions that make sense in the broader context of an organization's activities. It will be appreciated that one advantage to such an approach is that information flowing through an organization, and the networks they employ, should be trackable, and substantial data breaches preventable. Skilled practitioners of the art will recognize that many such embodiments and examples are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0076] FIG. 6 shows a simplified block diagram of an entity behavior profile (EBP) implemented in accordance with an embodiment of the invention. As used herein, an entity behavior profile 638 broadly refers to a collection of information that uniquely describes a particular entity's identity and their associated behavior, whether the behavior occurs within a physical realm or cyberspace. In certain embodiments, an EBP 638 may be used to adaptively draw inferences regarding the trustworthiness of a particular entity. In certain embodiments, as described in greater detail herein, the drawing of the inferences may involve comparing a new entity behavior to known past behaviors enacted by the entity. In certain embodiments, new entity behavior of analytic utility may represent entity behavior that represents a security risk. As likewise used herein, an entity broadly refers to something that exists as itself, whether physically or abstractly. In certain embodiments, an entity may be a user entity, a non-user entity, or a combination thereof. In certain embodiments, the identity of an entity may be known or unknown.
[0077] As used herein, a user entity broadly refers to an entity capable of enacting a user entity behavior, as described in greater detail herein. Examples of a user entity include an individual person, a group of people, an organization, or a government. As likewise used herein, a non-user entity broadly refers to an entity whose identity can be described and may exhibit certain behavior, but is incapable of enacting a user entity behavior. Examples of a non-user entity include an item, a device, such as endpoint and edge devices, a network, an account, a domain, an operation, a process, and an event. Other examples of a non-user entity include a resource, such as a geographical location or formation, a physical facility, a venue, a system, a software application, a data store, and a service, such as a service operating in a cloud environment.
[0078] Certain embodiments of the invention reflect an appreciation that being able to uniquely identity a device may assist in establishing whether or not a particular login is legitimate. As an example, user impersonations may not occur at the user's endpoint, but instead, from another device or system. Certain embodiments of the invention likewise reflect an appreciation that profiling the entity behavior of a particular device or system may assist in determining whether or not it is acting suspiciously.
[0079] In certain embodiments, an account may be local account, which runs on a single machine. In certain embodiments, an account may be a global account, providing access to multiple resources. In certain embodiments, a process may be implemented to run in an unattended mode, such as when backing up files or checking for software updates. Certain embodiments of the invention reflect an appreciation that it is often advantageous to track events at the process level as a method of determining which events are associated with background processes and which are initiated by a user entity.
[0080] In certain embodiments, an EBP 638 may be implemented to include a user entity profile 602, an associated user entity mindset profile 630, a non-user entity profile 632, and an entity state 636. As used herein, a user entity profile 602 broadly refers to a collection of information that uniquely describes a user entity's identity and their associated behavior, whether the behavior occurs within a physical realm or cyberspace. In certain embodiments, as described in greater detail herein, the user entity profile 602 may include user profile attributes 604, user behavior factors 610, user mindset factors 622, or a combination thereof. In certain embodiments, the user profile attributes 604 may include certain user authentication factors 606, described in greater detail herein, and personal information 608.
[0081] As used herein, a user profile attribute 604 broadly refers to data or metadata that can be used, individually or in combination with other user profile attributes 604, user behavior factors 610, or user mindset factors 622, to ascertain the identity of a user entity. In various embodiments, certain user profile attributes 604 may be uniquely associated with a particular user entity. In certain embodiments, the personal information 608 may include non-sensitive personal information associated with a user entity, such as their name, title, position, role, and responsibilities. In certain embodiments, the personal information 608 may likewise include technical skill level information, peer information, expense account information, paid time off (PTO) information, data analysis information, insider information, misconfiguration information, third party information, or a combination thereof. In certain embodiments, the personal information 608 may contain sensitive personal information associated with a user entity. As used herein, sensitive personal information (SPI), also commonly referred to as personally identifiable information (PII), broadly refers to any information usable to ascertain the identity of a user entity, either by itself, or in combination with other information, such as contextual information described in greater detail herein.
[0082] Examples of SPI may include the full or legal name of a user entity, initials or nicknames, place and date of birth, home and business addresses, personal and business telephone numbers, their gender, and other genetic information. Additional examples of SPI may include government-issued identifiers, such as a Social Security Number (SSN) or a passport number, vehicle registration plate and serial numbers, and driver's license numbers. Other examples of SPI may include certain email addresses and social media identifiers, credit and debit card numbers, and other digital identity information. Yet other examples of SPI may include employer-issued identifiers, financial transaction information, credit scores, electronic medical records (EMRs), insurance claim information, personal correspondence, and so forth. Further examples of SPI may include user authentication factors 606, such as biometrics, user identifiers and passwords, and personal identification numbers (PINs).
[0083] In certain embodiments, the SPI may include information considered by an individual user, a group of users, or an organization (e.g., a company, a government or non-government organization, etc.), to be confidential or proprietary. One example of such confidential information is protected health information (PHI). As used herein, PHI broadly refers to any information associated with the health status, provision of health care, or payment for health care that is created or collected by a “covered entity,” or an associate thereof, that can be linked to a particular individual. As used herein, a “covered entity” broadly refers to health plans, healthcare clearinghouses, healthcare providers, and others, who may electronically communicate any health-related information associated with a particular individual. Examples of such PHI may include any part of a patient's medical record, healthcare record, or payment history for medical or healthcare services.
[0084] As used herein, a user behavior factor 610 broadly refers to information associated with a user entity's behavior, whether the behavior occurs within a physical realm or cyberspace. In certain embodiments, user behavior factors 610 may include the user entity's access rights 612, the user entity's interactions 614, and the date/time/frequency 616 of when the interactions 614 are enacted. In certain embodiments, the user behavior factors 610 may likewise include the user entity's location 618, and the gestures 620 used by the user entity to enact the interactions 614.
[0085] In certain embodiments, the user entity gestures 620 may include key strokes on a keypad, a cursor movement, a mouse movement or click, a finger swipe, tap, or other hand gesture, an eye movement, or some combination thereof. In certain embodiments, the user entity gestures 620 may likewise include the cadence of the user's keystrokes, the motion, force and duration of a hand or finger gesture, the rapidity and direction of various eye movements, or some combination thereof. In certain embodiments, the user entity gestures 620 may include various audio or verbal commands performed by the user.
[0086] As used herein, user mindset factors 622 broadly refer to information used to make inferences regarding the mental state of a user entity at a particular point in time, during the occurrence of an event or an enactment of a user behavior, or a combination thereof. As likewise used herein, mental state broadly refers to a hypothetical state corresponding to the way a user entity may be thinking or feeling. Likewise, as used herein, an event broadly refers to the occurrence of an action performed by an entity. In certain embodiments, the user entity mindset factors 622 may include a personality type 624. Examples of known approaches for determining a personality type 624 include Jungian types, Myers-Briggs type indicators, Keirsey Temperament Sorter, Socionics, Enneagram of Personality, and Eyseneck's three-factor model.
[0087] In certain embodiments, the user mindset factors 622 may include various behavioral biometrics 626. As used herein, a behavioral biometric 628 broadly refers to a physiological indication of a user entity's mental state. Examples of behavioral biometrics 626 may include a user entity's blood pressure, heart rate, respiratory rate, eye movements and iris dilation, facial expressions, body language, tone and pitch of voice, speech patterns, and so forth.
[0088] Certain embodiments of the invention reflect an appreciation that certain user behavior factors 610, such as user entity gestures 620, may provide additional information related to inferring a user entity's mental state. As an example, a user entering text at a quick pace with a rhythmic cadence may indicate intense focus. Likewise, an individual user intermittently entering text with forceful keystrokes may indicate the user is in an agitated state. As another example, the user may intermittently enter text somewhat languorously, which may indicate being in a thoughtful or reflective state of mind. As yet another example, the user may enter text with a light touch with an uneven cadence, which may indicate the user is hesitant or unsure of what is being entered.
[0089] Certain embodiments of the invention likewise reflect an appreciation that while the user entity gestures 620 may provide certain indications of the mental state of a particular user entity, they may not provide the reason for the user entity to be in a particular mental state. Likewise, certain embodiments of the invention include an appreciation that certain user entity gestures 620 and behavioral biometrics 626 are reflective of an individual user's personality type 624. As an example, aggressive, forceful keystrokes combined with an increased heart rate may indicate normal behavior for a particular user when composing end-of-month performance reviews. In various embodiments, certain user entity behavior factors 610, such as user gestures 620, may be correlated with certain contextual information, as described in greater detail herein.
[0090] In certain embodiments, a security analytics system 118, described in greater detail herein, may be implemented to include an entity behavior catalog (EBC) system 120, or an entity behavior detection system 122, or both. In certain embodiments, the security analytics system 118 may be implemented to access a repository of event 670 data, a repository of EBC 690 data, and a repository of security analytics 680 data, or a combination thereof. In various embodiments, the security analytics system 118 may be implemented to use certain information stored in the repository of event 670 data, the repository of EBC 690 data, and the repository of security analytics 680 data, or a combination thereof, to perform a security analytics operation, described in greater detail herein. In certain embodiments, the results of a particular security analytics operation may be stored in the repository of security analytics 680 data.
[0091] In certain embodiments, the EBC system 120 may be implemented to generate, manage, store, or some combination thereof, information related to the behavior of an associated entity. In certain embodiments, the information related to the behavior of a particular entity may be stored in the form of an EBP 638. In certain embodiments, the EBC system 120 may be implemented to store the information related to the behavior of a particular entity in the repository of EBC 690 data. In various embodiments, the EBC system 120 may be implemented to generate certain information related to the behavior of a particular entity from event information associated with the entity, as described in greater detail herein. In certain embodiments, event information associated with a particular entity may be stored in the repository of event 670 data.
[0092] In various embodiments, the EBC system 120 may be implemented as a cyber behavior catalog. In certain of these embodiments, the cyber behavior catalog may be implemented to generate, manage, store, or some combination thereof, information related to cyber behavior, described in greater detail herein, enacted by an associated entity. In various embodiments, as likewise described in greater detail herein, the information generated, managed, stored, or some combination thereof, by such a cyber behavior catalog, may be related to cyber behavior enacted by a user entity, a non-user entity, or a combination thereof.
[0093] In certain embodiments, the security analytics system 118 may be implemented to include an entity behavior detection system 122. In certain embodiments, the entity behavior detection system 122 may be implemented to perform an entity behavior detection operation, likewise described in greater detail herein. In various embodiments, as likewise described in greater detail herein, the behavior detection system 122 may be implemented to use certain lexical information to perform the entity behavior detection operation.
[0094] As used herein, lexical information broadly refers to any information associated with a particular word, such as its definition, contextual meaning, synonyms, antonyms, denoted concepts, and so forth. In certain embodiments, the lexical information may be stored in a repository of lexicon 672 data. In certain embodiments, the lexical information stored in the repository of lexicon 672 data may be stored in the form of a lexicon.
[0095] As used herein, a lexicon broadly refers to a list of words. In certain embodiments, the list of words may be associated with a particular event, class of events, observable, class of observables, entity behavior, class of entity behaviors, security related activity, security related risk use case, or security vulnerability scenario, or a combination thereof, all of which are described in greater detail herein. In various embodiments, the lexical information may include words ontologically related to certain features, described in greater detail herein, associated with a particular entity behavior.
[0096] As used herein, ontologically related broadly refers to the way in which one object, such as a word, is related to another object in an ontology. In certain embodiments the ontological relationship may refer to the way in which one object is related to a class of objects, such as classes of words. In certain embodiments, the ontological relationship may be based upon one or more attributes shared by the objects or a class of objects. As likewise used herein, an object's attributes may broadly refer to an associated aspect, property, feature, characteristic, or parameter of the object.
[0097] As likewise used herein, an ontology broadly refers to any representation, formal naming, and definition of the categories, properties, and relations between the concepts, data, and entities that substantiate a particular domain of interest, such as security analytics. In various embodiments, the ontological relationship between certain words in a particular lexicon, and certain features associated with a particular entity behavior, may be advantageously used by the entity behavior detection system 122 to achieve more accurate results when performing an entity behavior detection operation. In various embodiments, as described in greater detail herein, the entity behavior detection system 122 may be implemented to use the ontological relationship to identify certain words in a particular lexicon that may be used to detect an entity behavior that may have otherwise not been detected.
[0098] In certain embodiments, a lexicon construction system 124 may be implemented, as described in greater detail herein, to generate a lexicon. In various embodiments, as likewise described in greater detail herein, the lexicon construction system 124 may be implemented to learn a lexicon by processing certain event information associated with entity behavior enacted by one or more entities. In certain embodiments, the lexicon construction system 124 may be implemented to store a learned lexicon in the repository of lexicon 672 data. In various embodiments, the lexicon construction system 124 may be implemented to provide certain lexical information stored in the repository of lexicon 672 data to the security analytics system 118 for use by the entity behavior detection system 122.
[0099] In certain embodiments, the EBC system 120 may be implemented to use a user entity profile 602 in combination with an entity state 636 to generate a user entity mindset profile 630. As used herein, entity state 636 broadly refers to the context of a particular event or entity behavior. In certain embodiments, the entity state 636 may be a long-term entity state or a short-term entity state. As used herein, a long-term entity state 636 broadly relates to an entity state 636 that persists for an extended interval of time, such as six months or a year. As likewise used herein, a short-term entity state 636 broadly relates to an entity state 636 that occurs for a brief interval of time, such as a few minutes or a day. In various embodiments, the method by which an entity state's 636 associated interval of time is considered to be long-term or short-term is a matter of design choice.
[0100] As an example, a particular user may have a primary work location, such as a branch office, and a secondary work location, such as their company's corporate office. In this example, the user's primary and secondary offices respectively correspond to the user's location 618, whereas the presence of the user at either office corresponds to an entity state 636. To continue the example, the user may consistently work at their primary office Monday through Thursday, but at their company's corporate office on Fridays. To further continue the example, the user's presence at their primary work location may be a long-term entity state 636, while their presence at their secondary work location may be a short-term entity state 636. Accordingly, a date/time/frequency 616 user entity behavior factor 610 can likewise be associated with user behavior respectively enacted on those days, regardless of their corresponding locations. Consequently, the long-term user entity state 636 on Monday through Thursday will typically be “working at the branch office” and the short-term entity state 636 on Friday will likely be “working at the corporate office.”
[0101] As likewise used herein, a user entity mindset profile 630 broadly refers to a collection of information that reflects an inferred mental state of a user entity at a particular time during the occurrence of an event or an enactment of a user behavior. As an example, certain information may be known about a user entity, such as their name, their title and position, and so forth, all of which are user profile attributes 604. Likewise, it may be possible to observe a user entity's associated user behavior factors 610, such as their interactions with various systems, when they log-in and log-out, when they are active at the keyboard, the rhythm of their keystrokes, and which files they typically use.
[0102] Certain embodiments of the invention reflect an appreciation these behavior factors 610 can be considered to be a behavioral fingerprint. In certain embodiments, the user behavior factors 610 may change, a little or a lot, from day to day. These changes may be benign, such as when a user entity begins a new project and accesses new data, or they may indicate something more concerning, such as a user entity who is actively preparing to steal data from their employer. In certain embodiments, the user behavior factors 610 may be implemented to ascertain the identity of a user entity. In certain embodiments, the user behavior factors 610 may be uniquely associated with a particular entity.
[0103] In certain embodiments, observed user behaviors may be used to build a user entity profile 602 for a particular user or other entity. In addition to creating a model of a user's various attributes and observed behaviors, these observations can likewise be used to infer things that are not necessarily explicit. Accordingly, in certain embodiments, a behavioral fingerprint may be used in combination with an EBP 638 to generate an inference regarding an associated user entity. As an example, a particular user may be observed eating a meal, which may or may not indicate the user is hungry. However, if it is also known that the user worked at their desk throughout lunchtime and is now eating a snack during a mid-afternoon break, then it can be inferred they are indeed hungry.
[0104] As likewise used herein, a non-user entity profile 632 broadly refers to a collection of information that uniquely describes a non-user entity's identity and their associated behavior, whether the behavior occurs within a physical realm or cyberspace. In various embodiments, the non-user entity profile 632 may be implemented to include certain non-user profile attributes 634. As used herein, a non-user profile attribute 634 broadly refers to data or metadata that can be used, individually or in combination with other non-user profile attributes 634, to ascertain the identity of a non-user entity. In various embodiments, certain non-user profile attributes 634 may be uniquely associated with a particular non-user entity.
[0105] In certain embodiments, the non-user profile attributes 634 may be implemented to include certain identity information, such as a non-user entity's network, Media Access Control (MAC), or physical address, its serial number, associated configuration information, and so forth. In various embodiments, the non-user profile attributes 634 may be implemented to include non-user behavior information associated with interactions between certain user and non-user entities, the type of those interactions, the data exchanged during the interactions, the date/time/frequency of such interactions, and certain services accessed or provided.
[0106] In various embodiments, the EBC system 120 may be implemented to use certain data associated with an EBP 638 to provide a probabilistic measure of whether a particular electronically-observable event is of analytic utility. In certain embodiments, an electronically-observable event that is of analytic utility may be determined to be anomalous, abnormal, unexpected, or malicious. To continue the prior example, a user may typically work out of their company's corporate office on Fridays. Furthermore, various user mindset factors 622 within their associated user entity profile 602 may indicate that the user is typically relaxed and methodical when working with customer data. Moreover, the user's user entity profile 602 indicates that such user interactions 614 with customer data typically occur on Monday mornings and the user rarely, if ever, copies or downloads customer data. However, the user may decide to interact with certain customer data late at night, on a Friday, while in their company's corporate office. As they do so, they exhibit an increased heart rate, rapid breathing, and furtive keystrokes while downloading a subset of customer data to a flash drive.
[0107] Consequently, their user entity mindset profile 630 may reflect a nervous, fearful, or guilty mindset, which is inconsistent with the entity state 634 of dealing with customer data in general. More particularly, downloading customer data late at night on a day the user is generally not in their primary office results in an entity state 634 that is likewise inconsistent with the user's typical user behavior. As a result, the EBC system 120 may infer that the user's behavior may represent a security threat. Those of skill in the art will recognize that many such embodiments and examples are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0108] Certain embodiments of the invention reflect an appreciation that the quantity, and relevancy, of information contained in a particular EBP 638 may have a direct bearing on its analytic utility when attempting to determine the trustworthiness of an associated entity and whether or not they represent a security risk. As used herein, the quantity of information contained in a particular EBP 638 broadly refers to the variety and volume of EBP elements it may contain, and the frequency of their respective instances, or occurrences, related to certain aspects of an associated entity's identity and behavior. As used herein, an EBP element broadly refers to any data element stored in an EBP 638, as described in greater detail herein. In various embodiments, an EBP element may be used to describe a particular aspect of an EBP, such as certain user profile attributes 604, user behavior factors 610, user mindset factors 622, user entity mindset profile 630, non-user profile attributes 634, and entity state 636.
[0109] In certain embodiments, statistical analysis may be performed on the information contained in a particular EBP 638 to determine the trustworthiness of its associated entity and whether or not they represent a security risk. For example, a particular authentication factor 606, such as a biometric, may be consistently used by a user entity for authenticating their identity to their endpoint device. To continue the example, a user ID and password may be used by the same, or a different user entity, in an attempt to access the endpoint device. As a result, the use of a user ID and password may indicate a security risk due to its statistical infrequency. As another example, a user entity may consistently access three different systems on a daily basis in their role as a procurement agent. In this example, the three systems may include a financial accounting system, a procurement system, and an inventory control system. To continue the example, an attempt by the procurement agent to access a sales forecast system may appear suspicious if never attempted before, even if the purpose for accessing the system is legitimate.
[0110] As likewise used herein, the relevancy of information contained in a particular EBP 638 broadly refers to the pertinence of the EBP elements it may contain to certain aspects of an associated entity's identity and behavior. To continue the prior example, an EBP 638 associated with the procurement agent may contain certain user profile attributes 604 related to their title, position, role, and responsibilities, all or which may be pertinent to whether or not they have a legitimate need to access the sales forecast system. In certain embodiments, the user profile attributes 604 may be implemented to include certain job description information. To further continue the example, such job description information may have relevance when attempting to determine whether or not the associated entity's behavior is suspicious. In further continuance of the example, job description information related to the procurement agent may include their responsibility to check sales forecast data, as needed, to ascertain whether or not to procure certain items. In these embodiments, the method by which it is determined whether the information contained in a particular EBP 638 is of sufficient quantity and relevancy is a matter of design choice.
[0111] Various embodiments of the invention likewise reflect an appreciation that accumulating sufficient information in an EBP 638 to make such a determination may take a certain amount of time. Likewise, various embodiments of the invention reflect an appreciation that the effectiveness or accuracy of such a determination may rely upon certain entity behaviors occurring with sufficient frequency, or in identifiable patterns, or a combination thereof, during a particular period of time. As an example, there may not be sufficient occurrences of a particular type of entity behavior to determine if a new entity behavior is inconsistent with known past occurrences of the same type of entity behavior. Accordingly, various embodiments of the invention reflect an appreciation that a sparsely-populated EBP 638 may likewise result in exposure to certain security vulnerabilities. Furthermore, the relevance of such sparsely-populated information initially contained in an EBP 638 first implemented may not prove very useful when using an EBP 638 to determine the trustworthiness of an associated entity and whether or not they represent a security risk.
[0112] FIGS. 7a and 7b show a block diagram of a security analytics environment implemented in accordance with an embodiment of the invention. In certain embodiments, a security analytics system 118 may be implemented with an entity behavior catalog (EBC) system 120, an entity behavior detection system 122, or both. In certain embodiments, analyses performed by the security analytics system 118 may be used to identify behavior associated with a particular entity that may be of analytic utility. In certain embodiments, as likewise described in greater detail herein, the EBC system 120, or the entity behavior detection system 122, or both, may be used in combination with the security analytics system 118 to perform such analyses. In various embodiments, certain data stored in a repository of security analytics 680 data, a repository of EBC 690 data, or a repository of event 670 data, or a combination thereof, may be used by the security analytics system 118, the EBC system 120, the entity behavior detection system 122, or some combination thereof, to perform the analyses.
[0113] In certain embodiments, the entity behavior detection system 122 may be implemented to perform an entity behavior detection operation, described in greater detail herein. In various embodiments, as likewise described in greater detail herein, the behavior detection system 122 may be implemented to use certain lexical information to perform the entity behavior detection operation. In certain embodiments, the lexical information may be stored in a repository of lexicon 672 data. In various embodiments, a lexicon construction system 124 may be implemented to provide certain lexical information stored in the repository of lexicon 672 data to the security analytics system 118 for use by the entity behavior detection system 122.
[0114] In certain embodiments, the lexicon construction system 124 may be implemented, as described in greater detail herein, to construct a lexicon. In various embodiments, as likewise described in greater detail herein, the lexicon construction system 124 may be implemented to learn a lexicon by processing certain event information associated with entity behavior enacted by one or more entities. In certain embodiments, the lexicon construction system 124 may be implemented to store a learned lexicon in the repository of lexicon 672 data.
[0115] In certain embodiments, the entity behavior of analytic utility may be identified at a particular point in time, during the occurrence of an event, the enactment of a user or non-user entity behavior, or a combination thereof. As used herein, an entity broadly refers to something that exists as itself, whether physically or abstractly. In certain embodiments, an entity may be a user entity, a non-user entity, or a combination thereof. In certain embodiments, a user entity may be an individual user, such as user ‘A’ 702 or ‘B’ 772, a group, an organization, or a government. In certain embodiments, a non-user entity may likewise be an item, a device, such as endpoint 304 and edge 202 devices, a network, such as an internal 744 and external 746 networks, a domain, an operation, or a process. In certain embodiments, a non-user entity may be a resource 750, such as a geographical location or formation, a physical facility 752, such as a venue, various physical security devices 754, a system 756, shared devices 758, such as printer, scanner, or copier, a data store 760, or a service 762, such as a service 762 operating in a cloud environment.
[0116] As likewise used herein, an event broadly refers to the occurrence of an action performed by an entity. In certain embodiments, the action may be directly associated with an entity behavior, described in greater detail herein. As an example, a first user may attach a binary file infected with a virus to an email that is subsequently sent to a second user. In this example, the act of attaching the binary file to the email is directly associated with an entity behavior enacted by the first user. In certain embodiments, the action may be indirectly associated with an entity behavior. To continue the example, the recipient of the email may open the infected binary file, and as a result, infect their computer with malware. To further continue the example, the act of opening the infected binary file is directly associated with an entity behavior enacted by the second user. However, the infection of the email recipient's computer by the infected binary file is indirectly associated with the described entity behavior enacted by the second user.
[0117] In various embodiments, certain user authentication factors 606 may be used to authenticate the identity of a user entity. In certain embodiments, the user authentication factors 606 may be used to ensure that a particular user entity, such as user ‘A’ 702 or ‘B’ 772, is associated with their corresponding user entity profile 602, rather than a user entity profile 602 associated with another user. In certain embodiments, the user authentication factors 606 may include a user's biometrics 706 (e.g., a fingerprint or retinal scan), tokens 708 (e.g., a dongle containing cryptographic keys), user identifiers and passwords (ID/PW) 710, and personal identification numbers (PINs).
[0118] In certain embodiments, information associated with such user entity behavior may be stored in a user entity profile 602, described in greater detail herein. In certain embodiments, the user entity profile 602 may be stored in a repository of entity behavior catalog (EBC) data 690. In certain embodiments, as likewise described in greater detail herein, the user entity profile 602 may include user profile attributes 604, user behavior factors 610, user mindset factors 622, or a combination thereof. As used herein, a user profile attribute 604 broadly refers to data or metadata that can be used, individually or in combination with other user profile attributes 604, user behavior factors 610, or user mindset factors 622, to ascertain the identity of a user entity. In various embodiments, certain user profile attributes 604 may be uniquely associated with a particular user entity.
[0119] As likewise used herein, a user behavior factor 610 broadly refers to information associated with a user's behavior, whether the behavior occurs within a physical realm or cyberspace. In certain embodiments, the user behavior factors 610 may include the user's access rights 612, the user's interactions 614, and the date/time/frequency 616 of those interactions 614. In certain embodiments, the user behavior factors 610 may likewise include the user's location 618 when the interactions 614 are enacted, and the user gestures 620 used to enact the interactions 614.
[0120] In various embodiments, certain date/time/frequency 616 user behavior factors 610 may be implemented as ontological or societal time, or a combination thereof. As used herein, ontological time broadly refers to how one instant in time relates to another in a chronological sense. As an example, a first user behavior enacted at 12:00 noon on May 17, 2017 may occur prior to a second user behavior enacted at 6:39 PM on May 18, 2018. Skilled practitioners of the art will recognize one value of ontological time is to determine the order in which various user behaviors have been enacted.
[0121] As likewise used herein, societal time broadly refers to the correlation of certain user profile attributes 604, user behavior factors 610, user mindset factors 622, or a combination thereof, to one or more instants in time. As an example, user ‘A’ 702 may access a particular system 756 to download a customer list at 3:47 PM on Nov. 3, 2017. Analysis of their user behavior profile indicates that it is not unusual for user ‘A’ 702 to download the customer list on a weekly basis. However, examination of their user behavior profile also indicates that user ‘A’ 702 forwarded the downloaded customer list in an email message to user ‘B’ 772 at 3:49 PM that same day. Furthermore, there is no record in their user behavior profile that user ‘A’ 702 has ever communicated with user ‘B’ 772 in the past. Moreover, it may be determined that user ‘B’ 872 is employed by a competitor. Accordingly, the correlation of user ‘A’ 702 downloading the customer list at one point in time, and then forwarding the customer list to user ‘B’ 772 at a second point in time shortly thereafter, is an example of societal time.
[0122] In a variation of the prior example, user ‘A’ 702 may download the customer list at 3:47 PM on Nov. 3, 2017. However, instead of immediately forwarding the customer list to user ‘B’ 772, user ‘A’ 702 leaves for a two week vacation. Upon their return, they forward the previously-downloaded customer list to user ‘B’ 772 at 9:14 AM on Nov. 20, 2017. From an ontological time perspective, it has been two weeks since user ‘A’ 702 accessed the system 756 to download the customer list. However, from a societal time perspective, they have still forwarded the customer list to user ‘B’ 772, despite two weeks having elapsed since the customer list was originally downloaded.
[0123] Accordingly, the correlation of user ‘A’ 702 downloading the customer list at one point in time, and then forwarding the customer list to user ‘B’ 772 at a much later point in time, is another example of societal time. More particularly, it may be inferred that the intent of user ‘A’ 702 did not change during the two weeks they were on vacation. Furthermore, user ‘A’ 702 may have attempted to mask an intended malicious act by letting some period of time elapse between the time they originally downloaded the customer list and when they eventually forwarded it to user ‘B’ 772. From the foregoing, those of skill in the art will recognize that the use of societal time may be advantageous in determining whether a particular entity behavior is of analytic utility. As used herein, mindset factors 622 broadly refer to information used to infer the mental state of a user at a particular point in time, during the occurrence of an event, an enactment of a user behavior, or combination thereof.
[0124] In certain embodiments, the security analytics system 118 may be implemented to process certain entity attribute information, described in greater detail herein, associated with providing resolution of the identity of an entity at a particular point in time. In various embodiments, the security analytics system 118 may be implemented to use certain entity identifier information, likewise described in greater detail herein, to ascertain the identity of an associated entity at a particular point in time. In various embodiments, the entity identifier information may include certain temporal information, described in greater detail herein. In certain embodiments, the temporal information may be associated with an event associated with a particular point in time.
[0125] In certain embodiments, the security analytics system 118 may be implemented to use information associated with certain entity behavior elements to resolve the identity of an entity at a particular point in time. An entity behavior element, as used herein, broadly refers to a discrete element of an entity's behavior during the performance of a particular operation in a physical realm, cyberspace, or a combination thereof. In certain embodiments, such entity behavior elements may be associated with a user/device 730, a user/network 742, a user/resource 748, a user/user 770 interaction, or a combination thereof.
[0126] As an example, user ‘A’ 702 may use an endpoint device 304 to browse a particular web page on a news site on an external system 776. In this example, the individual actions performed by user ‘A’ 702 to access the web page are entity behavior elements that constitute an entity behavior, described in greater detail herein. As another example, user ‘A’ 702 may use an endpoint device 304 to download a data file from a particular system 756. In this example, the individual actions performed by user ‘A’ 702 to download the data file, including the use of one or more user authentication factors 606 for user authentication, are entity behavior elements that constitute an entity behavior. In certain embodiments, the user/device 730 interactions may include an interaction between a user, such as user ‘A’ 702 or ‘B’ 772, and an endpoint device 304.
[0127] In certain embodiments, the user/device 730 interaction may include interaction with an endpoint device 304 that is not connected to a network at the time the interaction occurs. As an example, user ‘A’ 702 or ‘B’ 772 may interact with an endpoint device 304 that is offline, using applications 732, accessing data 734, or a combination thereof, it may contain. Those user/device 730 interactions, or their result, may be stored on the endpoint device 304 and then be accessed or retrieved at a later time once the endpoint device 304 is connected to the internal 744 or external 746 networks. In certain embodiments, an endpoint agent 306 may be implemented to store the user/device 730 interactions when the user device 304 is offline.
[0128] In certain embodiments, an endpoint device 304 may be implemented with a device camera 728. In certain embodiments, the device camera 728 may be integrated into the endpoint device 304. In certain embodiments, the device camera 728 may be implemented as a separate device configured to interoperate with the endpoint device 304. As an example, a webcam familiar to those of skill in the art may be implemented receive and communicate various image and audio signals to an endpoint device 304 via a Universal Serial Bus (USB) interface.
[0129] In certain embodiments, the device camera 728 may be implemented to capture and provide user/device 730 interaction information to an endpoint agent 306. In various embodiments, the device camera 728 may be implemented to provide surveillance information related to certain user/device 730 or user/user 770 interactions. In certain embodiments, the surveillance information may be used by the security analytics system 118 to detect entity behavior associated with a user entity, such as user ‘A’ 702 or user ‘B’ 772 that may be of analytic utility.
[0130] In certain embodiments, the endpoint device 304 may be used to communicate data through the use of an internal network 744, an external network 746, or a combination thereof. In certain embodiments, the internal 744 and the external 746 networks may include a public network, such as the Internet, a physical private network, a virtual private network (VPN), or any combination thereof. In certain embodiments, the internal 744 and external 746 networks may likewise include a wireless network, including a personal area network (PAN), based on technologies such as Bluetooth. In various embodiments, the wireless network may include a wireless local area network (WLAN), based on variations of the IEEE 802.11 specification, commonly referred to as WiFi. In certain embodiments, the wireless network may include a wireless wide area network (WWAN) based on an industry standard including various 3G, 4G and 5G technologies.
[0131] In certain embodiments, the user/user 770 interactions may include interactions between two or more user entities, such as user ‘A’ 702 and ‘B’ 772. In certain embodiments, the user/user interactions 770 may be physical, such as a face-to-face meeting, via a user/device 730 interaction, a user/network 742 interaction, a user/resource 748 interaction, or some combination thereof. In certain embodiments, the user/user 770 interaction may include a face-to-face verbal exchange. In certain embodiments, the user/user 770 interaction may include a written exchange, such as text written on a sheet of paper. In certain embodiments, the user/user 770 interaction may include a face-to-face exchange of gestures, such as a sign language exchange.
[0132] In certain embodiments, temporal event information associated with various user/device 730, user/network 742, user/resource 748, or user/user 770 interactions may be collected and used to provide real-time resolution of the identity of an entity at a particular point in time. Those of skill in the art will recognize that many such examples of user/device 730, user/network 742, user/resource 748, and user/user 770 interactions are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0133] In various embodiments, the security analytics system 118 may be implemented to process certain contextual information in the performance of certain security analytic operations. As used herein, contextual information broadly refers to any information, directly or indirectly, individually or in combination, related to a particular entity behavior. In certain embodiments, entity behavior may include a user entity's physical behavior, cyber behavior, or a combination thereof. As likewise used herein, a user entity's physical behavior broadly refers to any user behavior occurring within a physical realm, such as speaking, gesturing, facial patterns or expressions, walking, and so forth. More particularly, such physical behavior may include any action enacted by an entity user that can be objectively observed, or indirectly inferred, within a physical realm. In certain embodiments, the objective observation, or indirect inference, of the physical behavior may be performed electronically.
[0134] As an example, a user may attempt to use an electronic access card to enter a secured building at a certain time. In this example, the use of the access card to enter the building is the action and the reading of the access card makes the user's physical behavior electronically-observable. As another example, a first user may physically transfer a document to a second user, which is captured by a video surveillance system. In this example, the physical transferal of the document from the first user to the second user is the action. Likewise, the video record of the transferal makes the first and second user's physical behavior electronically-observable. As used herein, electronically-observable user behavior broadly refers to any behavior exhibited or enacted by a user entity that can be observed through the use of an electronic device (e.g., an electronic sensor), a computing device or system (e.g., an endpoint 304 or edge 202 device, a physical security device 754, a system 756, a shared device 758, etc.), computer instructions (e.g., a software application), or a combination thereof.
[0135] Cyber behavior, as used herein, broadly refers to any behavior occurring in cyberspace, whether enacted by an individual user, a group of users, or a system acting at the behest of an individual user, a group of users, or other entity. More particularly, cyber behavior may include physical, social, or mental actions that can be objectively observed, or indirectly inferred, within cyberspace. As an example, a user may use an endpoint device 304 to access and browse a particular website on the Internet. In this example, the individual actions performed by the user to access and browse the website constitute a cyber behavior. As another example, a user may use an endpoint device 304 to download a data file from a particular system 756 at a particular point in time. In this example, the individual actions performed by the user to download the data file, and associated temporal information, such as a time-stamp associated with the download, constitute a cyber behavior. In these examples, the actions are enacted within cyberspace, in combination with associated temporal information, which makes them electronically-observable.
[0136] In certain embodiments, the contextual information may include location data 736. In certain embodiments, the endpoint device 304 may be configured to receive such location data 736, which is used as a data source for determining the user's location 618. In certain embodiments, the location data 736 may include Global Positioning System (GPS) data provided by a GPS satellite 738. In certain embodiments, the location data 736 may include location data 736 provided by a wireless network, such as from a cellular network tower 740. In certain embodiments (not shown), the location data 736 may include various Internet Protocol (IP) or other network address information assigned to the endpoint 304 or edge 202 device. In certain embodiments (also not shown), the location data 736 may include recognizable structures or physical addresses within a digital image or video recording.
[0137] In certain embodiments, the endpoint devices 304 may include an input device (not shown), such as a keypad, magnetic card reader, token interface, biometric sensor, and so forth. In certain embodiments, such endpoint devices 304 may be directly, or indirectly, connected to a particular facility 752, physical security device 754, system 756, or shared device 758. As an example, the endpoint device 304 may be directly connected to an ingress/egress system, such as an electronic lock on a door or an access gate of a parking garage. As another example, the endpoint device 304 may be indirectly connected to a physical security device 754 through a dedicated security network.
[0138] In certain embodiments, the security analytics system 118 may be implemented to perform various risk-adaptive protection operations. Risk-adaptive, as used herein, broadly refers to adaptively responding to risks associated with an electronically-observable entity behavior. In various embodiments, the security analytics system 118 may be implemented to perform certain risk-adaptive protection operations by monitoring certain entity behaviors, assess the corresponding risk they may represent, individually or in combination, and respond with an associated response. In certain embodiments, such responses may be based upon contextual information, described in greater detail herein, associated with a given entity behavior.
[0139] In certain embodiments, various information associated with a user entity profile 602, likewise described in greater detail herein, may be used to perform the risk-adaptive protection operations. In certain embodiments, the user entity profile 602 may include user profile attributes 604, user behavior factors 610, user mindset factors 622, or a combination thereof. In these embodiments, the information associated with a user entity profile 602 used to perform the risk-adaptive protection operations is a matter of design choice.
[0140] In certain embodiments, the security analytics system 118 may be implemented as a stand-alone system. In certain embodiments, the security analytics system 118 may be implemented as a distributed system. In certain embodiment, the security analytics system 118 may be implemented as a virtual system, such as an instantiation of one or more virtual machines (VMs). In certain embodiments, the security analytics system 118 may be implemented as a security analytics service 764. In certain embodiments, the security analytics service 764 may be implemented in a cloud environment familiar to those of skill in the art. In various embodiments, certain operations performed by the lexicon construction system 124 may be offered as an aspect of the security analytics service 764. In various embodiments, the security analytics system 118 may use data stored in a repository of security analytics 680 data, EBC 690 data, event 670 data, and lexicon 672 data, or a combination thereof, in the performance of certain security analytics operations, described in greater detail herein. Those of skill in the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0141] FIG. 8 is a simplified block diagram showing the mapping of an event to a security vulnerability scenario implemented in accordance with an embodiment of the invention. In certain embodiments, an entity behavior catalog (EBC) system 120 may be implemented to identify a security related activity, described in greater detail herein. In certain embodiments, the security related activity may be based upon an observable, likewise described in greater detail herein. In certain embodiments, the observable may include event information corresponding to electronically-observable behavior enacted by an entity. In certain embodiments, the event information corresponding to electronically-observable behavior enacted by an entity may be received from an electronic data source, such as the EBC data sources 810 shown in FIGS. 8, 15, 16 b, and 17.
[0142] In certain embodiments, as likewise described in greater detail herein, the EBC system 120 may be implemented to identify a particular event of analytic utility by analyzing an associated security related activity. In certain embodiments, the EBC system 120 may be implemented to generate entity behavior catalog data based upon an identified event of analytic utility associated with a particular security related activity. In various embodiments, the EBC system 120 may be implemented to associate certain entity behavior data it may generate with a predetermined abstraction level, described in greater detail herein.
[0143] In various embodiments, the EBC system 120 may be implemented to use certain EBC data 690 and an associated abstraction level to generate a hierarchical set of entity behaviors 870, described in greater detail herein. In certain embodiments, the hierarchical set of entity behaviors 870 generated by the EBC system 120 may represent an associated security risk, likewise described in greater detail herein. Likewise, as described in greater detail herein, the EBC system 120 may be implemented in certain embodiments to store the hierarchical set of entity behaviors 870 and associated abstraction level information within a repository of EBC data 690. In certain embodiments, the repository of EBC data 690 may be implemented to provide an inventory of entity behaviors for use when performing a security operation, likewise described in greater detail herein.
[0144] Referring now to FIG. 8 , the EBC system 120 may be implemented in various embodiments to receive certain event information, described in greater detail herein, corresponding to an event associated with an entity interaction. As used herein, event information broadly refers to any information directly or indirectly related to an event. As likewise used herein, an event broadly refers to the occurrence of at least one action performed by an entity. In certain embodiments, the at least one action performed by an entity may include the enactment of an entity behavior, described in greater detail herein. In certain embodiments, the entity behavior may include an entity's physical behavior, cyber behavior, or a combination thereof, as likewise described in greater detail herein.
[0145] Likewise, as used herein, an entity interaction broadly refers to an action influenced by another action enacted by an entity. As an example, a first user entity may perform an action, such as sending a text message to a second user entity, who in turn replies with a response. In this example, the second user entity's action of responding is influenced by the first user entity's action of sending the text message. In certain embodiments, an entity interaction may include the occurrence of at least one event enacted by one entity when interacting with another, as described in greater detail herein. In certain embodiments, an event associated with an entity interaction may include at least one entity attribute, described in greater detail herein, and at least one entity behavior, likewise described in greater detail herein.
[0146] In certain embodiments, an entity attribute and an entity behavior may be respectively abstracted to an entity attribute 872 and an entity behavior 874 abstraction level. In certain embodiments, an entity attribute 872 and an entity behavior 874 abstraction level may then be associated with an event 876 abstraction level. In certain embodiments, the entity attribute 872, entity behavior 874, and event 876 abstraction levels may in turn be associated with a corresponding entity behavior hierarchy 870, as described in greater detail herein.
[0147] In various embodiments, the event information may be received from certain EBC data sources 810, such as a user 802 entity, an endpoint 804 non-user entity, a network 806 non-user entity, or a system 808 non-user entity. In certain embodiments, one or more events may be associated with a particular entity interaction. As an example, as shown in FIG. 8 , one or more events i+n 812 may be associated with a user/device 730 interaction between a user 802 entity and an endpoint 904 non-user entity. Likewise, one or more events j+n 814 may be associated with a user/network 742 interaction between a user 802 entity and a network 806 non-user entity. As likewise shown in FIG. 8 , one or more events k+n 916 816 may be associated with a user/resource 748 interaction between a user 802 entity and a system 808 non-user entity.
[0148] In certain embodiments, details of an event, such as events i+n 812, j+n 814, and k+n 816, may be included in their associated event information. In various embodiments, as described in greater detail herein, analytic utility detection operations may be performed on such event information to identify events of analytic utility. In various embodiments, certain event information associated with an event determined to be of analytic utility may be used to derive a corresponding observable. As used herein, an observable broadly refers to an event of analytic utility whose associated event information may include entity behavior that may be anomalous, abnormal, unexpected, malicious, or some combination thereof, as described in greater detail herein.
[0149] As an example, the details contained in the event information respectively corresponding to events i+n 812, j+n 814, and k+n 816 may be used to derive observables i+n 822, j+n 824, and k+n 826. In certain embodiments, the resulting observables i+n 822, j+n 824, and k+n 826 may then be respectively associated with a corresponding observable 878 abstraction level. In certain embodiments, the observable 878 abstraction level may in turn be associated with a corresponding entity behavior hierarchy 870, as described in greater detail herein.
[0150] In certain embodiments, the resulting observables may in turn be processed to generate an associated security related activity. As used herein, a security related activity broadly refers to an abstracted description of an interaction between two entities, described in greater detail herein, which may represent anomalous, abnormal, unexpected, or malicious entity behavior. For example, observables i+n 822, j+n 824, and k+n 826 may in turn be processed to generate corresponding security related activities i 832, j 834, and k 836. In certain embodiments, the resulting security related activities, i 832, j 834, and k 836 may then be respectively associated with a corresponding security related activity 880 abstraction level. In certain embodiments, the security related activity 880 abstraction level may in turn be associated with a corresponding entity behavior hierarchy 870, as described in greater detail herein.
[0151] In various embodiments, sessionization and fingerprint generation operations 820, described in greater detail herein, may be performed to associate certain events, observables, and security related activities, or a combination thereof, with a corresponding session, likewise described in greater detail herein. As an example, events i+n 812, j+n 814, k+n 816, observables i+n 822, j+n 824, k+n 826, and security related activities i 832, j 834, k 836 may be associated with corresponding sessions. In certain embodiments, a security related activity may be processed with associated contextual information, described in greater detail herein, to generate a corresponding EBP element.
[0152] For example, security related activities i 832, j 834, and k 836 may be processed with associated contextual information to generate corresponding EBP elements i 842, j 844, and k 846. In various embodiments, the resulting EBP elements i 842, j 844, and k 846 may then be associated with a corresponding EBP element 882 abstraction level. In certain embodiments, the EBP element 882 abstraction level may in turn be associated with a corresponding entity behavior hierarchy 870, as described in greater detail herein.
[0153] In certain embodiments, EBP generation and modification 840 operations may be performed to associate one or more EBP elements with a particular EBP 638. As an example, EBP elements i 842, j 844, and k 946 may be associated with a particular EBP 638, which may likewise be respectively associated with the various entities involved in the user/device 730, user/network 742, or user/resource 748 interactions. In these embodiments, the method by which the resulting EBP elements i 842, j 844, and k 846 are associated with a particular EBP 638 is a matter of design choice. In certain embodiments, the EBP 638 may likewise associated with an EBP 884 abstraction level. In certain embodiments, the EBP 884 abstraction level may in turn be associated with a corresponding entity behavior hierarchy 870, as described in greater detail herein.
[0154] In various embodiments, the resulting EBP 638 may be used in the performance of security risk use case association 850 operations to identify one or more security risk use cases that match certain entity behavior information stored in the EBP 638. As used herein, a security risk use case broadly refers to a set of security related activities that create a security risk narrative that can be used to adaptively draw inferences, described in greater detail herein, from entity behavior enacted by a particular entity. In certain of these embodiments, the entity behavior information may be stored within the EBP 638 in the form of an EBP element, a security related activity, an observable, or an event, or a combination thereof. In certain embodiments, identified security risk use cases may then be associated with a security risk use case 886 abstraction level. In certain embodiments, the security risk use case 886 abstraction level may in turn be associated with a corresponding entity behavior hierarchy 870, as described in greater detail herein.
[0155] In certain embodiments, the results of the security risk use case association 850 operations may in turn be used to perform security vulnerability scenario inference 860 operations to associate one or more security risk use cases with one or more security vulnerability scenarios. As used herein, a security vulnerability scenario broadly refers to a grouping of one or more security risk use cases that represent a particular class of security vulnerability. In certain embodiments, the associated security vulnerability scenarios may then be associated with a security vulnerability scenario 888 abstraction level. In certain embodiments, the security vulnerability scenario 888 abstraction level may in turn be associated with a corresponding entity behavior hierarchy 870, as described in greater detail herein.
[0156] In various embodiments, certain event information associated with events i+n 812, j+n 814, and k+n 816 and certain observable information associated with observables i+n 822, j+n 824, and k+n 826 may be stored in a repository of EBC data 690. In various embodiments, certain security related activity information associated with security related activities i 832, j 834, and k 836 and EBP elements i 842, j 844, and k 846 may likewise be stored in the repository of EBC data 690. Likewise, in various embodiments, certain security risk use case association and security vulnerability scenario association information respectively associated with the performance of security risk use case association 850 and security vulnerability scenario inference 860 operations may be stored in the repository of EBC data 690.
[0157] FIG. 9 is a simplified block diagram of the generation of a session and a corresponding session-based fingerprint implemented in accordance with an embodiment of the invention. In certain embodiments, an observable 906 may be derived from an associated event, as described in greater detail herein. In certain embodiments, one or more observables 906 may be processed to generate a corresponding security related activity 908. In certain embodiments, one or more security related activities 908 may then be respectively processed to generate a corresponding activity session 910. In turn, the session 910 may be processed in certain embodiments to generate a corresponding session fingerprint 912. In certain embodiments, the resulting activity session 910 and its corresponding session fingerprint 912, individually or in combination, may then be associated with a particular entity behavior profile (EBP) element 980. In certain embodiments the EBP element 980 may in turn be associated with an EBP 638.
[0158] In certain embodiments, intervals in time 904 respectively associated with various security related activities 908 may be contiguous. For example, as shown in FIG. 9 , the intervals in time 904 associated with observables 906 ‘1’ 914 and ‘2’ 916 may be contiguous. Accordingly, the intervals in time 904 associated with the security related activities 908 ‘1’ 918 and ‘2’ 920 respectively generated from observables 906 ‘1’ 914 and ‘2’ 916 would likewise be contiguous.
[0159] As likewise shown in FIG. 9 , the resulting security related activities 908 ‘1’ 918 and ‘2’ 920 may be processed to generate an associated activity session ‘A’ 922, which then may be processed to generate a corresponding session fingerprint ‘A’ 924. In certain embodiments, activity session ‘A’ 922 and its corresponding session fingerprint ‘A’ 924 may be used to generate a new entity behavior profile (EBP) element 980 ‘A’ 926. In certain embodiments, EBP element 980 ‘A’ 926 generated from activity session 910 ‘A’ 922 and its corresponding session fingerprint 912 ‘A’ 924 may be associated with an existing EBP 638.
[0160] To provide an example, a user may enact various observables 906 ‘1’ 914 to update sales forecast files, followed by the enactment of various observables 906 ‘2’ 1016 to attach the updated sales forecast files to an email, which is then sent to various co-workers. In this example, the enactment of observables 906 ‘1’ 914 and ‘2’ 916 result in the generation of security related activities 908 ‘1’ 918 and ‘2’ 920, which in turn are used to generate activity session 910 ‘A’ 922. In turn, the resulting activity session 910 ‘A’ 922 is then used to generate its corresponding session-based fingerprint 912 ‘A’ 924. To continue the example, activity session 910 ‘A’ 922 is associated with security related activities 908 ‘1’ 918 and ‘2’ 920, whose associated intervals in time 904 are contiguous, as they are oriented to the updating and distribution of sales forecast files via email.
[0161] Various aspects of the invention reflect an appreciation that a user may enact certain entity behaviors on a recurring basis. To continue the preceding example, a user may typically update sales forecast files and distribute them to various co-workers every morning between 8:00 AM and 10:00 AM. Accordingly, the activity session 910 associated with such a recurring activity may result in a substantively similar session fingerprint 912 week-by-week. However, a session fingerprint 912 for the same session 910 may be substantively different should the user happen to send an email with an attached sales forecast file to a recipient outside of their organization. Consequently, a session fingerprint 912 that is inconsistent with session fingerprints 912 associated with past activity sessions 910 may indicate anomalous, abnormal, unexpected or malicious behavior.
[0162] In certain embodiments, two or more activity sessions 910 may be noncontiguous, but associated. In certain embodiments, an activity session 910 may be associated with two or more sessions 910. In certain embodiments, an activity session 910 may be a subset of another activity session 910. As an example, as shown in FIG. 9 , the intervals in time 904 respectively associated with observables 906 ‘3’ 914 and ‘6’ 932 may be contiguous. Likewise, the intervals in time 904 associated with observables 906 ‘4’ 936 and ‘5’ 938 may be contiguous.
[0163] Accordingly, the intervals in time 904 associated with the security related activities 908 ‘4’ 936 and ‘5’ 938 respectively generated from observables 906 ‘4’ 928 and ‘5’ 930 would likewise be contiguous. However, the intervals in time 904 associated with security related activities 908 ‘4’ 936 and ‘5’ 938 would not be contiguous with the intervals in time respectively associated with security related activities 908 ‘3’ 934 and ‘6’ 940.
[0164] As likewise shown in FIG. 9 , the resulting security related activities 908 ‘3’ 934 and ‘6’ 940 may be respectively processed to generate corresponding sessions ‘B’ 942 and ‘D’ 946, while security related activities 908 ‘4’ 936 and ‘5’ 938 may be processed to generate activity session 910 ‘C’ 944. In turn, activity sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946 are then respectively processed to generate corresponding session-based fingerprints 912 ‘B’ 948, ‘C’ 950 and ‘D’ 952.
[0165] Accordingly, the intervals of time 904 respectively associated with activity sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946, and their corresponding session fingerprints 912 ‘B’ 948, ‘C’ 950 and ‘D’ 952, are not contiguous. Furthermore, in this example activity sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946, and their corresponding session fingerprints 912 ‘B’ 948, ‘C’ 950 and ‘D’ 952, are not associated with the EBP 638. Instead, as shown in FIG. 9 , activity sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946 are processed to generate activity session 910 ‘E’ 954 and session fingerprints 912 ‘B’ 948, ‘C’ 950 and ‘D’ 952 are processed to generate session fingerprint 912 ‘E’ 956. In certain embodiments, activity session ‘E’ 954 and its corresponding session fingerprint ‘E’ 956 may be used to generate a new EBP element 980 ‘E’ 958. In certain embodiments, EBP element 980 ‘E’ 958 generated from activity session 910 ‘E’ 954 and its corresponding session fingerprint 912 ‘E’ 956 may be associated with an existing EBP 638.
[0166] Accordingly, session 910 ‘E’ 1054 is associated with activity sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946. Likewise, sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946 are subsets of session 910 ‘E’ 954. Consequently, while the intervals of time respectively associated with activity sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946, and their corresponding session fingerprints 912 ‘B’ 948, ‘C’ 950 and ‘D’ 952 may not be contiguous, they are associated as they are respectively used to generate session 910 ‘E’ 954 and its corresponding session fingerprint 912 ‘E’ 1056.
[0167] To provide an example, a user plans to attend a meeting scheduled for 10:00 AM at a secure facility owned by their organization to review a project plan with associates. However, the user wishes to arrive early to prepare for the meeting. Accordingly, they arrive at 9:00 AM and use their security badge to authenticate themselves and enter the facility. In this example, the enactment of observables 906 ‘3’ 926 may correspond to authenticating themselves with their security badge and gaining access to the facility. As before, observables 906 ‘3’ 926 may be used to generate a corresponding security related activity 908 ‘3’ 934. In turn, the security related activity 908 ‘3’ 934 may then be used to generate session 910 ‘B’ 942, which is likewise used in turn to generate a corresponding session fingerprint 912 ‘B’ 948.
[0168] The user then proceeds to a conference room reserved for the meeting scheduled for 10:00 AM and uses their time alone to prepare for the upcoming meeting. Then, at 10:00 AM, the scheduled meeting begins, followed by the user downloading the current version of the project plan, which is then discussed by the user and their associate for a half hour. At the end of the discussion, the user remains in the conference room and spends the next half hour making revisions to the project plan, after which it is uploaded to a datastore for access by others.
[0169] In this example, observables 906 ‘4’ 928 may be associated with the user downloading and reviewing the project plan and observables 906 ‘5’ 930 may be associated with the user making revisions to the project plan and then uploading the revised project plan to a datastore. Accordingly, behavior elements 906 ‘4’ 928 and ‘5’ 930 may be respectively used to generate security related activities 908 ‘4’ 936 and ‘5’ 938. In turn, the security related activities 908 ‘4’ 936 and ‘5’ 938 may then be used to generate session 910 ‘C’ 944, which may likewise be used in turn to generate its corresponding session-based fingerprint 912 ‘C’ 950.
[0170] To continue the example, the user may spend the next half hour discussing the revisions to the project plan with a co-worker. Thereafter, the user uses their security badge to exit the facility. In continuance of this example, observables 906 ‘6’ 932 may be associated with the user using their security badge to leave the secure facility. Accordingly, observables 906 ‘6’ 932 may be used to generate a corresponding security related activity 908 ‘6’ 940, which in turn may be used to generate a corresponding session 910 ‘D’ 946, which likewise may be used in turn to generate a corresponding session fingerprint 912 ‘D’ 952.
[0171] In this example, the intervals of time 904 respectively associated with activity sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946, and their corresponding session fingerprints 912 ‘B’ 948, ‘C’ 950, and ‘D’ 952, are not contiguous. However they may be considered to be associated as their corresponding observables 906 ‘3’ 926, ‘4’ 928, ‘5’ 930, and ‘6’ 932 all have the common attribute of having been enacted within the secure facility. Furthermore, security related activities 908 ‘4’ 936 and ‘5’ 938 may be considered to be associated as their corresponding observables 906 have the common attribute of being associated with the project plan.
[0172] Accordingly, while the intervals of time 904 respectively associated with activity sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946, and their corresponding session-based fingerprints 912 ‘B’ 948, ‘C’ 950, and ‘D’ 952, may not be contiguous, they may be considered to be associated. Consequently, sessions 910 ‘B’ 942, ‘C’ 944, and ‘D’ 946 may be considered to be a subset of session 910 ‘E’ 954 and session-based fingerprints 912 ‘B’ 948, ‘C’ 950, and ‘D’ 952 may be considered to be a subset of session-based fingerprint 912 ‘E’ 956.
[0173] In certain embodiments, the interval of time 904 corresponding to a first activity session 910 may overlap an interval of time 904 corresponding to a second activity session 910. For example, observables 906 ‘7’ 958 and ‘8’ 960 may be respectively processed to generate security related activities 908 ‘7’ 962 and ‘8’ 964. In turn, the resulting security related activities 908 ‘7’ 962 and ‘8’ 964 are respectively processed to generate corresponding activity sessions 910 ‘F’ 966 and ‘G’ 968. Sessions The resulting activity sessions 910 ‘F’ 966 and ‘G’ 968 are then respectively processed to generate corresponding session-based fingerprints 912 ‘F’ 970 and ‘G’ 972.
[0174] However, in this example activity sessions 910 ‘F’ 966 and ‘G’ 968, and their corresponding session fingerprints 912 ‘F’ 970 and ‘G’ 972, are not associated with the EBP 638. Instead, as shown in FIG. 9 , activity sessions 910 ‘F’ 966 and ‘G’ 968 are processed to generate activity session 910 ‘E’ 954 and session fingerprints 912 ‘F’ 970 and ‘G’ 972 are processed to generate session fingerprint 912 ‘H’ 976. In certain embodiments, activity session ‘H’ 974 and its corresponding session fingerprint ‘H’ 976 may be used to generate a new EBP element 980 ‘H’ 978. In certain embodiments, EBP element 980 ‘H’ 978 generated from activity session 910 ‘E’ 974 and its corresponding session fingerprint 912 ‘E’ 976 may be associated with an existing EBP 638.
[0175] Accordingly, the time 904 interval associated with activity session 910 ‘F’ 966 and its corresponding session fingerprint 912 ‘F’ 970 overlaps with the time interval 904 associated with activity session 910 ‘G’ 968 and its corresponding session fingerprint 912 ‘G’ 972. As a result, activity sessions 910 ‘F’ 966 and ‘G’ 968 are subsets of activity session 910 ‘H’ 974. Consequently, while the intervals of time respectively associated with activity sessions 910 ‘F’ 966 and ‘G’ 968, and their corresponding session fingerprints 912 ‘F’ 970 and ‘G’ 972 may overlap, they are associated as they are respectively used to generate activity session 910 ‘H’ 974 and its corresponding session fingerprint 912 ‘H’ 976.
[0176] To provide an example, a user may decide to download various images for placement in an online publication. In this example, observables 906 ‘7’ 958 may be associated with the user iteratively searching for, and downloading, the images they wish to use in the online publication. However, the user may not begin placing the images into the online publication until they have selected and downloaded the first few images they wish to use.
[0177] To continue the example, observables 906 ‘8’ may be associated with the user placing the downloaded images in the online publication. Furthermore, the placement of the downloaded images into the online publication may begin a point in time 904 subsequent to when the user began to download the images. Moreover, the downloading of the images may end at a point in time 904 sooner than when the user completes the placement of the images in the online publication.
[0178] In continuance of the example, observables 906 ‘7’ 958 and ‘8’ 960 may be respectively processed to generate security related activities 908 ‘7’ 962 and ‘8’ 964, whose associated intervals of time 904 overlap one another. Accordingly, the intervals in time 904 associated with activity sessions 910 ‘F’ 966 and ‘G’ 968 will likewise overlap one another as they are respectively generated from security related activities 908 ‘7’ 962 and ‘8’ 964.
[0179] Consequently, while the intervals of time 904 respectively associated with activity sessions 910 ‘F’ 966 and ‘G’ 968, and their corresponding session fingerprints 912 ‘F’ 970 and ‘G’ 972, may overlap, they may be considered to be associated as they both relate to the use of images for the online publication. Accordingly, activity sessions 910 ‘F’ 1066 and ‘G’ 968 may be considered to be a subset of activity session 910 ‘H’ 974 and session fingerprints 912 ‘F’ 970 and ‘G’ 972 may be considered to be a subset of session fingerprint 912 ‘H’ 976.
[0180] FIG. 10 is a generalized flowchart of session fingerprint generation operations performed in accordance with an embodiment of the invention. In this embodiment, activity session fingerprint generation operations are begun in step 1002, followed by the selection of an entity in step 1004 for associated entity behavior profile (EBP) element generation. As used herein, an EBP element broadly refers to any data element stored in an EBP, as described in greater detail herein. In various embodiments, an EBP element may be used to describe a particular aspect of an EBP, such as certain entity behaviors enacted by an entity associated with the EBP. Ongoing monitoring operations are then performed in step 1006 to monitor the selected entity's behavior to detect the occurrence of an event, described in greater detail herein.
[0181] A determination is then made in step 1008 whether an event has been detected. If not, then a determination is made in step 1026 whether to continue monitoring the entity's behavior to detect an event. If so, then the process is continued, proceeding with step 1006. Otherwise, session fingerprint generation operations are ended in step 1028. However, if it was determined in step 1008 that an event was detected, then event data associated with the detected event is processed to determine whether the event is of analytic utility, as described in greater detail herein.
[0182] A determination is then made in step 1012 to determine whether the event is of analytic utility. If not, then the process is continued, proceeding with 1026. Otherwise, an observable, described in greater detail herein, is derived from the event in step 1014. The resulting observable is then processed with associated observables in step 1016, as likewise described in greater detail herein, to generate a security related activity. As likewise described in greater detail herein, the resulting security related activity is then processed in step 1018 with associated security related activities to generate an activity session.
[0183] In turn, the resulting activity session is then processed in step 1020 to generate a corresponding session fingerprint. The resulting session fingerprint is then processed with its corresponding activity session in step 1022 to generate an associated EBP element. The resulting EBP element is then added to an EPB associated with the entity in step 1024 and the process is then continued, proceeding with step 1026.
[0184] FIG. 11 is simplified block diagram of process flows associated with the operation of an entity behavior catalog (EBC) system implemented in accordance with an embodiment of the invention. In certain embodiments, the EBC system 120 may be implemented to define and manage an entity behavior profile (EBP) 638, as described in greater detail herein. In certain embodiments, the EBP 638 may be implemented to include a user entity profile 602, a user entity mindset profile 632, a non-user entity profile 634, and an entity state 636, or a combination thereof, as likewise described in greater detail herein.
[0185] In certain embodiments, the EBC system 120 may be implemented use a particular user entity profile 602 in combination with a particular entity state 638 to generate an associated user entity mindset profile 632, likewise as described in greater detail herein. In certain embodiments, the EBC system 120 may be implemented to use the resulting user entity mindset profile 632 in combination with its associated user entity profile 602, non-user entity profile 634, and entity state 638, or a combination thereof, to detect entity behavior of analytic utility. In various embodiments, the EBC system 120 may be implemented to perform EBP management 1124 operations to process certain entity attribute and entity behavior information, described in greater detail herein, associated with defining and managing an EBP 638.
[0186] As used herein, entity attribute information broadly refers to information associated with a particular entity. In various embodiments, the entity attribute information may include certain types of content. In certain embodiments, such content may include text, unstructured data, structured data, graphical images, photographs, audio recordings, video recordings, biometric information, and so forth. In certain embodiments, the entity attribute information may include metadata. In certain embodiments, the metadata may include entity attributes, which in turn may include certain entity identifier types or classifications.
[0187] In certain embodiments, the entity attribute information may include entity identifier information. In various embodiments, the EBC system 120 may be implemented to use certain entity identifier information to ascertain the identity of an associated entity at a particular point in time. As used herein, entity identifier information broadly refers to an information element associated with an entity that can be used to ascertain or corroborate the identity of its corresponding entity at a particular point in time. In certain embodiments, the entity identifier information may include user authentication factors, user entity 602 and non-user entity 634 profile attributes, user and non-user entity behavior factors, user entity mindset factors, information associated with various endpoint and edge devices, networks, and resources, or a combination thereof.
[0188] In certain embodiments, the entity identifier information may include temporal information. As used herein, temporal information broadly refers to a measure of time (e.g., a date, timestamp, etc.), a measure of an interval of time (e.g., a minute, hour, day, etc.), or a measure of an interval of time (e.g., two consecutive weekdays days, or between Jun. 3, 2017 and Mar. 4, 2018, etc.). In certain embodiments, the temporal information may be associated with an event associated with a particular point in time. As used herein, such a temporal event broadly refers to an occurrence, action or activity enacted by, or associated with, an entity at a particular point in time.
[0189] Examples of such temporal events include making a phone call, sending a text or an email, using a device, such as an endpoint device, accessing a system, and entering a physical facility. Other examples of temporal events include uploading, transferring, downloading, modifying, or deleting data, such as data stored in a datastore, or accessing a service. Yet other examples of temporal events include interactions between two or more users, interactions between a user and a device, interactions between a user and a network, and interactions between a user and a resource, whether physical or otherwise. Yet still other examples of temporal events include a change in name, address, physical location, occupation, position, role, marital status, gender, association, affiliation, or assignment.
[0190] As likewise used herein, temporal event information broadly refers to temporal information associated with a particular event. In various embodiments, the temporal event information may include certain types of content. In certain embodiments, such types of content may include text, unstructured data, structured data, graphical images, photographs, audio recordings, video recordings, and so forth. In certain embodiments, the temporal event information may include metadata. In various embodiments, the metadata may include temporal event attributes, which in turn may include certain entity identifier types or classifications, described in greater detail herein.
[0191] In certain embodiments, the EBC system 120 may be implemented to use information associated with such temporal resolution of an entity's identity to assess the risk associated with a particular entity, at a particular point in time, and respond with a security operation 1128, described in greater detail herein. In certain embodiments, the EBC system 120 may be implemented to respond to such assessments in order to reduce operational overhead and improve system efficiency while maintaining associated security and integrity. In certain embodiments, the response to such assessments may be performed by a security administrator. Accordingly, certain embodiments of the invention may be directed towards assessing the risk associated with the affirmative resolution of the identity of an entity at a particular point in time in combination with its behavior and associated contextual information. Consequently, the EBC system 120 may be more oriented in various embodiments to risk adaptation than to security administration.
[0192] Referring now to FIG. 11 , in certain embodiments, EBC system 120 operations are begun with the receipt of information associated with an initial event i 1102. In certain embodiments, information associated with an initial event i 1102 may include user entity profile 602 attributes, user behavior factors, user entity mindset factors, entity state information, contextual information, all described in greater detail herein, or a combination thereof. In various embodiments, certain user entity profile 602 data, user entity mindset profile 632 data, non-user entity profile 634 data, entity state 636 data, contextual information, and temporal information stored in a repository of EBC data 690 may be retrieved and then used to perform event enrichment 1108 operations to enrich the information associated with event i 1102.
[0193] In certain embodiments, the event enrichment 1108 operations may include the performance of one or more entity behavior detection 1110 operations, described in greater detail herein. In certain embodiments, the entity behavior detection 1110 operations may be performed by an entity behavior detection system, described in greater detail herein. In various embodiments, certain lexical information stored in a repository of lexicon data 672 may be used to perform the entity behavior detection 1110 operations. In certain embodiments, the event enrichment 1108 operations may be performed without performing any associated entity behavior detection 1110 operations. Those of skill in the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope, or intent of the invention.
[0194] Analytic utility detection 1112 operations are then performed on the resulting enriched event i 1102 to determine whether it is of analytic utility. If so, then it is derived as an observable 906, described in greater detail herein. In certain embodiments, event i+l 1104 through event i+n 1106, may in turn be received by the EBC system 120 and be enriched 1008. Analytic utility detection 1112 operations are then performed on the resulting enriched event i+l 1104 through event i+n 1106 to determine whether they are of analytic utility. Observables 906 are then derived from those that are.
[0195] In certain embodiments, security related activity abstraction 1114 operations may be performed on the resulting observables 906 corresponding to events i 1102, i+l 1104, i+n 1106 to generate an associated security related activity 908, described in greater detail herein. In various embodiments, a security related activity 908 may be expressed in a Subject→Action→Object format and associated with observables 906 resulting from event information provided by various received from certain EBC data sources, likewise described in greater detail herein. In certain embodiments, a security related activity abstraction 1114 operation may be performed to abstract away EBC data source-specific knowledge and details when expressing an entity behavior. For example, rather than providing the details associated with a “Windows:4624” non-user entity event, its details may be abstracted to “User Login To Device” security related activity 908.
[0196] In various embodiments, sessionization and fingerprint 820 operations, described in greater detail herein, may be performed on event information corresponding to events i 1102, i+l 1104, i+n 1106, their corresponding observables 906, and their associated security related activities 908, or a combination thereof, to generate session information. In various embodiments, the resulting session information may be used to associate certain events i 1102, i+l 1104, i+n 1106, or their corresponding observables 906, or their corresponding security related activities 908, or a combination thereof, with a particular session.
[0197] In certain embodiments, as likewise described in greater detail herein, one or more security related activities 908 may in turn be associated with a corresponding EBP element. In various embodiments, the previously-generated session information may be used to associate the one or more security related activities 908 with a particular EBP element. In certain embodiments, the one or more security related activities 908 may be associated with its corresponding EBP element through the performance of an EBP management 1124 operation. Likewise, in certain embodiments, one or more EBP elements may in turn be associated with the EBP 638 through the performance of an EBP management 1124 operation.
[0198] In various embodiments, certain contextualization information stored in the repository of EBC data 690 may be retrieved and then used to perform entity behavior contextualization 1118 operations to provide entity behavior context, based upon the entity's user entity profile 602, or non-user entity profile 634, and its associated entity state 638. In various embodiments, security risk use case association 1118 operations may be performed to associate an EBP 638 with a particular security risk use case. In certain embodiments, the results of the previously-performed entity behavior contextualization 1118 operations may be used to perform the security risk use case association 850 operations.
[0199] In various embodiments, security vulnerability scenario inference 860 operations may be performed to associate a security risk use case with a particular security vulnerability scenario, described in greater detail herein. In various embodiments, certain observables 906 derived from events of analytical utility may be used to perform the security vulnerability scenario inference 860 operations. In various embodiments, certain entity behavior contexts resulting from the performance of the entity behavior contextualization 1118 operations may be used to perform the security vulnerability scenario inference 860 operations.
[0200] In certain embodiments, entity behavior meaning derivation 1126 operations may be performed on the security vulnerability behavior scenario selected as a result of the performance of the security vulnerability scenario inference 860 operations to derive meaning from the behavior of the entity. In certain embodiments, the entity behavior meaning derivation 1126 operations may be performed by analyzing the contents of the EBP 638 in the context of the security vulnerability behavior scenario selected as a result of the performance of the security vulnerability scenario inference 860 operations. In certain embodiments, the derivation of entity behavior meaning may include inferring the intent of an entity associated with event event i 1102 and event i+l 1104 through event i+n 1106.
[0201] In various embodiments, performance of the entity behavior meaning derivation 1126 operations may result in the performance of a security operation 1128, described in greater detail herein. In certain embodiments, the security operation 1128 may include a risk-adaptive protection 1132 operation. In certain embodiments, the risk-adaptive protection 1132 operation may include adaptively responding with an associated risk-adaptive response, as described in greater detail herein.
[0202] In various embodiments, the security operation 1128 may include certain risk mitigation operations being performed by a security administrator. As an example, performance of the security operation 1128 may result in a notification being sent to a security administrator alerting them to the possibility of suspicious behavior. In certain embodiments, the security operation 1128 may include certain risk mitigation operations being automatically performed by a security analytics system or service. As an example, performance of the security operation 1128 may result in a user's access to a particular system being disabled if an attempted access occurs at an unusual time or from an unknown device.
[0203] In certain embodiments, meaning derivation information associated with event i 1102 may be used to update the user entity profile 602 or non-user entity profile 634 corresponding to the entity associated with event event i 1102. In certain embodiments, the process is iteratively repeated, proceeding with meaning derivation information associated with event i+l 1104 through event i+n 1106. From the foregoing, skilled practitioners of the art will recognize that a user entity profile 602, or a non-user entity profile 634, or the two in combination, as implemented in certain embodiments, not only allows the identification of events associated with a particular entity that may be of analytic utility, but also provides higher-level data that allows for the contextualization of observed events. Accordingly, by viewing individual sets of events both in context and with a view to how they may be of analytic utility, it is possible to achieve a more nuanced and higher-level comprehension of an entity's intent.
[0204] FIG. 12 is a simplified block diagram of process flows implemented in accordance with an embodiment of the invention for constructing a lexicon for use in detecting entity behavior of analytic utility. In certain embodiments, a corpus 1202 of training events, such as training events ‘1’ 1204, and ‘2’ 1206 through ‘n’ 1208 shown in FIG. 12 is identified for analysis. In certain embodiments, the event information may be in the form of structured content, unstructured content, or a combination thereof. In certain embodiments, individual training events (e.g., events ‘1’ 1204, and ‘2’ 1206 through ‘n’ 1208) within the corpus 1202 may then be parsed in step 1210 to identify associated terms. In certain embodiments, the identified terms may be of analytical utility, described in greater detail herein.
[0205] As used herein, a term broadly refers to a word, compound word, phrase expression, numeric value, or alphanumeric string, which in certain contexts is associated with a particular meaning. As likewise used herein, a phrase broadly refers to a sequence of terms, or multi-words, familiar to skilled practitioners of the art. In certain embodiments, a term may be associated with an event, a feature of an event, a classification label, a metadata tag label, or a combination thereof.
[0206] As used herein, a feature, as it relates to an event, broadly refers to a property, characteristic, or attribute of a particular event. As an example, features associated with a corpus of thousands of text-oriented messages (e.g., SMS, email, social network messages, etc.) may be generated by removing low-value words (i.e., stopwords), using certain size blocks of words (i.e., n-grams), or applying various text processing rules. Examples of features associated with an event may include the number of bytes uploaded, the time of day, the presence of certain terms in unstructured content, the respective domains associated with senders and recipients of information, and the Uniform Resource Locator (URL) classification of certain web page visits. In certain embodiments, such features may be associated with anomalous, abnormal, unexpected or malicious user behavior, as described in greater detail herein.
[0207] In certain embodiments, entity information may include entity feature information, entity attribute information, or a combination thereof. As used herein, entity feature information broadly refers to information commonly used to perform analysis operations associated with entity models. As likewise used herein, entity attribute information broadly refers to structured information associated with a particular entity. In certain embodiments, entity attribute information may include one or more attribute types. An attribute type, as likewise used herein, broadly refers to a class of attributes, such as a Boolean attribute type, a double attribute type, a string attribute type, a date attribute type, and so forth.
[0208] As used herein, a Boolean attribute type broadly refers to a type of Boolean operator, familiar to those of skill in the art, associated with a particular event or associated entity. Known examples of such Boolean operator types include conjunction, disjunction, exclusive disjunction, implication, biconditional, negation, joint denial, and alternative denial. In certain embodiments, a Boolean event attribute type may be implemented to simplify data management operations. As an example, it may be more efficient to associate a biconditional Boolean event attribute having values of “true” and “false” to an event data field named “Privileges,” rather than assigning the values “Privileged” and “Nonprivileged.”
[0209] As used herein, a double attribute type broadly refers to a type of attribute that includes a numeric value associated with a particular entity or event. In certain embodiments, a double attribute type may be implemented for the performance of range searches for values, such as values between 10 and 25. In certain embodiments, a double attribute type may be implemented to configure numeric data field features, such as identifying unusually high or unusually low numeric values. In certain embodiments, a double attribute type may be implemented to create event models that aggregate by the max or sum of various event attribute values. Skilled practitioners of the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0210] As used herein, a string attribute type broadly refers to a type of attribute that includes a string of characters associated with an entity or an event. In certain embodiments, a string attribute type may include text characters, numeric values, mathematical operators (e.g., ‘+’, ‘*’, etc.), or a combination thereof. As an example, a string attribute may for an entity data field named “Participants” may include the character string “2 hosts+3 assistants+37 attendees.” In certain embodiments, a string attribute type may be implemented to search for partial matches of a particular value, such as a reference to a “java” file.
[0211] As used herein, a date attribute type broadly refers to a type of attribute that contains a natural date associated with an entity or an event. In certain embodiments, the representation or format of a particular date (e.g., Mar. 15, 2018, 3/15/2018, etc.), or time (e.g., 1:07 PM, 13:07:23, etc.) is a matter of design choice. In certain embodiments, a date attribute type may be implemented to perform searches for a particular date, a particular time, or a combination thereof. In certain embodiments, a date attribute type may be implemented to perform searches for a range of dates, a range of time, or a combination thereof.
[0212] In certain embodiments, the event information may include event content information, event timestamp information, event attachment information, event reference information, or a combination thereof. As used herein, event content information broadly refers to an unstructured body of text associated with a particular event. As an example, the main body of a communication, such as an email, a Short Message Service (SMS) text, a Chat communication, or a Twitter™ Tweet™ contains event content information.
[0213] In various embodiments, search operations may be performed on certain event content information to identify particular information. In certain embodiments, such search operations may include the use of lexicon features familiar to skilled practitioners of the art. In certain embodiments such search operations may include the use of sentiment features, likewise familiar to those of skill in the art. In certain of these embodiments, extraction operations may be performed on the event content information to extract such identified information.
[0214] In certain embodiments, the event content information may be processed to generate structured data. In certain embodiments, the event content information may be processed to generate an event summary, described in greater detail herein. In these embodiments, the method by which the event content information is processed, and the form of the resulting structured data or event summary is generated, is a matter of design choice.
[0215] As used herein, event timestamp information broadly refers to time and date information associated with the time and date an event occurred. Examples of such timestamp information include the time and date an email was sent, the time and date a user logged-in to a system, the time and date a user printed a file, and so forth. Other examples of such timestamp information include the time and date a particular Data Loss Prevention (DLP) alert was generated, as well as the time and date the DLP event occurred. Yet other examples of such timestamp information include the actual time and date of a particular event, and the publically-reported time and date of the occurrence of the event. Additional examples of such timestamp information include the time and date of a meeting invite, the time and date the invite was generated, the time(s) and date(s) of any rescheduling of the meeting, or a combination thereof.
[0216] As used herein, event attachment information broadly refers to a separate body of content having an explicit association with a particular event. One example of such event attachment information includes a file. In certain embodiments, such a file may be an unstructured text file, a structured data file, an audio file, an image file, a video file, and so forth. Another example of such event attachment information includes a hypertext link, familiar to those of skill in the art, to a separate body of content. In certain embodiments, the linked body of content may include unstructured text, structured data, image content, audio content, video content, additional hypertext links, or a combination thereof.
[0217] In certain embodiments, event attachment information may be ingested and processed to identify associated entity and event information, as described in greater detail herein. In various embodiments, the event attachment information may be processed to determine certain metadata, such as the size of an attached file, the creator of the event attachment information, the time and date it was created, and so forth. In certain embodiments, search operations may be performed on the event attachment information to identify certain information associated with a particular event.
[0218] As used herein, event reference information broadly refers to information related to commonalities shared between two or more events. As an example, two events may have a parent/child, or chain, relationship. To further the example, the sending of a first email may result in the receipt of a second email. In turn, a third email may be sent from the receiver of the second email to a third party. In this example, the event reference information would include the routing information associated with the first, second and third emails, which form an email chain.
[0219] In certain embodiments, event information may be processed to generate an event summary. As used herein, an event summary broadly refers to a brief, unstructured body of text that summarizes certain information with a particular event. In certain embodiments, the event summary may summarize information associated with an event. As an example, the subject line of an email may include such an event summary. In various embodiments, a group of event summaries may be searched during the performance of certain security analytics operations, described in greater detail herein, to identify associated event information.
[0220] In certain embodiments, natural language processing (NLP) and other approaches familiar to skilled practitioners of the art may be used to perform the parsing. As an example, event information associated with a particular training event may include an audio recording of human language being spoken. In this example, the event information may be processed to generate a digital transcript of the recording, which in turn may be parsed to identify certain words it may contain. As another example, the event information may include hand-written text. In this example, image recognition approaches familiar to those of skill in the art may be used to convert the hand-written content into a digital form, which in turn may be parsed to identify certain words it may contain.
[0221] As yet another example, the event information may include a segment of unstructured text. In this example, various NLP approaches may be used to process the unstructured text to extract certain words it may contain and then determine synonyms, antonyms, or associated concepts for those words. Skilled practitioners of the art will recognize many such examples of using NLP and other approaches for parsing operations are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0222] The terms parsed in step 1210 from the event information respectively associated with individual training events in the event stream 1202 are then processed in step 1212 to extract relevant vectors, and group the terms into topic clusters. In various embodiments, certain topic modeling approaches familiar to those of skill in the art may be used to group the terms into associated topic clusters. The resulting topic clusters are likewise analyzed in step 1212 to cluster the training events into classified clusters, which in turn are then assigned labels. For example, as shown in FIG. 12 , training events ‘1’ 1204, and ‘2’ 1206 through ‘n’ 1208 may be grouped into classified clusters 1214 relative to vectors 1216, 1218 according to their respectively associated terms.
[0223] For example, terms associated with a first training event may contain the terms “love,” “chocolates,” and “valentine card,” while terms associated with a second training event may contain the terms “roses,” and “February 14.” In this example, the terms “love,” “chocolates,” “valentine card,” “roses,” and “February 14” are all related to terms commonly associated with Valentine's Day. Accordingly, the first and second training event would be grouped into the same classified cluster 1214. In certain embodiments, unsupervised machine learning approaches familiar to skilled practitioners of the art may be implemented to automatically group training events ‘1’ 1204, and ‘2’ 1206 through ‘n’ 1208 into classified clusters 1214.
[0224] As likewise shown in FIG. 12 , the resulting classified clusters 1214 of training events are then respectively assigned labels of cluster ‘1’ 1220, ‘2’ 1222, ‘3’ 1224, and ‘4’ 1226. In these embodiments, the method by which training events ‘1’ 1204, and ‘2’ 1206 through ‘n’ 1208 may be grouped into classified clusters 1214, and the number of vectors 1216, 1218 they may be relative to, and the labels they may be assigned, is a matter of design choice. Likewise, while only two vectors 1216, 1218 are shown in FIG. 12 , skilled practitioners of the art will recognize that it is possible to group classified clusters relative to many vectors. Accordingly, the foregoing is not intended to limit the spirit, scope, or intent of the invention.
[0225] Analysis operations are then performed in step 1228 on terms associated with each of the classified clusters 1214 of training events. In various embodiments, the analysis operations may include a statistical analysis of how often certain terms occur within training events associated with a particular classified cluster 1214. In turn, the results of the analysis operations performed in step 1228 are then used in step 1230 to derive learned lexicons.
[0226] As an example, terms associated with cluster ‘1’ 1220 shown in FIG. 12 may include “booze,” “drunk,” “DUI,” and so forth, indicating that the events corresponding cluster ‘1’ 1220 are likely alcohol-related. Accordingly, the terms associated with cluster ‘1’ 1220 may be derived to construct a learned lexicon of alcohol-related words. As another example, terms associated with cluster ‘2’ 1222 may include “marijuana,” “SKED,” “possession,” and so forth, indicating that the events corresponding to cluster ‘2’ 1222 are likely drug-related. Accordingly, the terms associated with cluster ‘2’ 1222 may be derived to construct a learned lexicon of drug-related words. Likewise, the terms respectively associated with clusters ‘3’ 1224 and ‘4’ 1226 may be derived to construct learned lexicons of words associated with criminal conduct and financial concerns. In certain embodiments, the learned lexicons may be derived manually, automatically, or a combination thereof.
[0227] In various embodiments, the learned lexicons derived in step 1230 may be used to perform certain entity behavior detection operations 1110, described in greater detail herein. In certain embodiments, the entity behavior operations 1110 may include using the learned lexicons to process event information associated with individual training events to generate enriched events 1232, such as enriched events ‘a’ 1234, and ‘b’ 1236 through ‘c’ 1238. In certain embodiments, the enriched events 1232 may be used in step 1240 to reevaluate and tune learned lexicons. In certain embodiments, the reevaluation and tuning of learned lexicons may include providing the enriched events 1232 as additional training events, which can then be used in step 1212, as described in greater detail herein.
[0228] In certain embodiments, entity behavior detection operations 1110 may be performed on a stream of monitored events 1242. In various embodiments, the enriched events 1232 resulting from the performance of certain entity behavior detection operations 1110 may be used to perform a security operation 1128, likewise described in greater detail herein, on a particular monitored event 1242. In various embodiments, the security operation 1128 may include analyzing certain terms associated with one or more learned lexicons derived in step 1230. In various embodiments, the enriched events 1232 resulting from certain entity behavior detection operations 1110 may be used to perform a security operation 1128 associated with detecting 1244 entity behavior of analytic utility. Those of skill in the art will recognize many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope, or intent of the invention.
[0229] FIG. 13 is a table showing components of an entity behavior profile (EBP) implemented in accordance with an embodiment of the invention. In various embodiments, an EBP 638 may be implemented to certain include entity attributes 1304 behavioral models 1306, and inferences 1308, along with entity state 636. In certain embodiments, an EBP's 638 entity state 636 may be short-term, or reflect the state of an entity at a particular point or interval in time. In certain embodiments, an EBP's 638 entity state 636 may be long-term, or reflect the state of an entity at recurring points or intervals in time.
[0230] In certain embodiments, an EBP's 638 associated entity attributes 1304 may be long-lived. As an example, a particular user entity may have a name, an employee ID, an assigned office, and so forth, all of which are facts rather than insights. In certain embodiments, a particular entity state 636 may be sufficiently long-termed to be considered an entity attribute 1304. As an example, a first user and a second user may both have an entity state 636 of being irritable. However, the first user may have a short-term entity state 636 of being irritable on an infrequent basis, while the second user may have a long-term entity state 636 of be irritable on a recurring basis. In this example, the long-term entity state 636 of the second user being irritable may be considered to be an entity attribute 1304. In various embodiments, the determination of what constitutes an entity state 636 and an entity attribute 1304 is a matter of design choice. In certain embodiments, various knowledge representation approaches may be implemented in combination with an entity behavior catalog (EBC) system to understand the ontological interrelationship of entity attributes 1304 one or more EBP's 638 may contain. In these embodiments, the method by which certain entity attributes 1304 are selected to be tracked by an EBC system, and the method by which they are managed within a corresponding EBP 638, is a matter of design choice.
[0231] In certain embodiments, the ATP 638 evolves over time as new events and entity behavior is detected. In certain embodiments, an ATP's 638 associated behavioral models 1306, and thus the ATP 638 itself may evolve over time. In certain embodiments, an ATP's 638 behavioral models 1306 may be used by an ATP system to provide insight into how unexpected a set of events may be. As an example, a behavioral model 1306 may include information related to where a particular user entity works, which devices they may use and locations they may login from, who they may communicate with, and so forth. Certain embodiments of the invention reflect an appreciation that such behavioral models 1306 can be useful when comparing observed user and non-user entity behaviors to past observations in order to determine how unusual a particular entity behavior may be.
[0232] For example, a user may have more than one EBP 638 associated with a particular channel, which as used herein broadly refers to a medium capable of supporting the electronic observation of a user or non-user behavior, such as a keyboard, a network, a video stream, and so forth. To continue the example, the user may have a particular set of people he sends emails to from his desktop computer, and does so in an orderly and methodical manner, carefully choosing his words, and writing longer than average messages compared to his peers. Consequently, analysis of such an email message will likely indicate it was authored by the user and not someone else.
[0233] However, the same user may also send emails from a second channel, which is his mobile telephone. When using his mobile telephone, the user's emails are typically short, contains typos and emojis, and his writing style is primarily limited to simple confirmations or denials. Consequently, analysis of one such email would likely not reveal whether the user was the author or not, due to its brevity. Accordingly, the use of the same channel, which in this example is email, demonstrates the use of different devices will likely generate different behavioral models 1306, which in turn could affect the veracity of associated inferences 1308.
[0234] In certain embodiments, a behavioral model 1306 may be implemented as a session-based fingerprint. As used herein, a session-based fingerprint broadly refers to a unique identifier of an enactor of user or non-user behavior associated with a session. In certain embodiments, the session-based fingerprint may be implemented to determine how unexpected an event may be, based upon an entity's history as it relates to the respective history of their peer entities. In certain embodiments, the session-based fingerprint may be implemented to determine whether an entity associated with a particular session is truly who they or it claims to be or if they are being impersonated. In certain embodiments, the session-based fingerprint may be implemented to determine whether a particular event, or a combination thereof, may be of analytic utility. In certain embodiments, the session-based fingerprint may include a risk score, be used to generate a risk score, or a combination thereof.
[0235] As likewise used herein, a fingerprint, as it relates to a session, broadly refers to a collection of information providing one or more distinctive, characteristic indicators of the identity of an enactor of one or more corresponding user or non-user entity behaviors during the session. In certain embodiments, the collection of information may include one or more user or non-user profile elements. A user or non-user profile element, as used herein, broadly refers to a collection of user or non-user entity behavior elements, described in greater detail herein.
[0236] As used herein, inferences 1308 broadly refer to things that can be inferred about an entity based upon observations. In certain embodiments the observations may be based upon electronically-observable behavior, described in greater detail herein. In certain embodiments, the behavior may be enacted by a user entity, a non-user entity, or a combination thereof. In certain embodiments, inferences 1308 may be used to provide insight into a user entity's mindset or affective state.
[0237] As an example, an inference 1308 may be made that a user is unhappy in their job or that they are facing significant personal financial pressures. Likewise, based upon the user's observed behavior, an inference 1308 may be made that they are at a higher risk of being victimized by phishing schemes due to a propensity for clicking on random or risky website links. In certain embodiments, such inferences 1308 may be implemented to generate a predictive quantifier of risk associated with an entity's behavior.
[0238] In certain embodiments, entity state 636, described in greater detail herein, may be implemented such that changes in state can be accommodated quickly while reducing the overall volatility of a particular EBP 638. As an example, a user may be traveling by automobile. Accordingly, the user's location is changing quickly. Consequently, location data is short-lived. As a result, while the location of the user may not be updated within their associated EBP 638 as it changes, the fact their location is changing may prove to be useful in terms of interpreting other location-based data from other sessions. To continue the example, knowing the user is in the process of changing their location may assist in explaining why the user appears to be in two physical locations at once.
[0239] FIG. 14 is an activities table showing analytic utility actions occurring during a session implemented in accordance with an embodiment of the invention. In certain embodiments, an entity behavior catalog (EBC) system, described in greater detail herein, may be implemented to capture and record various entity actions 1404 enacted by an entity during a session 1402, likewise described in greater detail herein. In certain embodiments, the actions, and their associated sessions, may be stored in an entity behavior profile (EBP) corresponding to a particular entity. In various embodiments, the EBC system may be implemented to process information stored in an EBP to determine, as described in greater detail herein, which actions 1404 enacted by a corresponding entity during a particular session 1402 may be of analytic utility 1408.
[0240] Certain embodiments of the invention reflect an appreciation that multiple sessions 1402, each of which may be respectively associated with a corresponding entity, may occur within the same interval of time 1406. Certain embodiments of the invention likewise reflect an appreciation that a single action of analytic utility 1408 enacted by an entity occurring during a particular interval of time 1406 may not appear to be suspicious behavior by an associated entity. Likewise, certain embodiments of the invention reflect an appreciation that the occurrence of multiple actions of analytic utility 1408 enacted by an entity during a particular session 1402 may be an indicator of suspicious behavior.
[0241] Certain embodiments reflect an appreciation that a particular entity may be associated with two or more sessions 1402 that occur concurrently over a period of time 1406. Certain embodiments of the invention likewise reflect an appreciation that a single action of analytic utility 1408 enacted by an entity occurring during a first session 1402 may not appear to be suspicious. Conversely, certain embodiments of the invention reflect an appreciation that multiple actions of analytic utility 1308 during a second session 1402 may be enacted by an entity.
[0242] As an example, a user may log into the same system from two different IP addresses, one associated with their laptop computer and the other their mobile phone. In this example, entity actions 1404 enacted by the user using their laptop computer may be associated with a first session 1402 (e.g. session ‘2’), and entity actions 1404 enacted by the user using their mobile phone may be associated with a second session 1402 (e.g., session ‘3’). To continue the example, only one action of analytic utility 1408 may be associated with the first session 1402, while three actions of analytic utility 1408 may be associated with the second session 1402. Accordingly, it may be inferred the preponderance of actions of analytic utility 1408 enacted by the user during the second session 1402 may indicate suspicious behavior being enacted with their mobile phone.
[0243] FIGS. 15a and 15b are a generalized flowchart of the performance of entity behavior catalog (EBC) system operations implemented in accordance with an embodiment of the invention. In this embodiment, EBC system operations are begun in step 1502 with ongoing operations being performed by the EBC system in step 1504 to monitor the receipt of event information to detect the occurrence of an event, described in greater detail herein.
[0244] A determination is then made in step 1506 to determine whether an event has been detected. If not, then a determination is made in step 1536 to determine whether to continue monitoring the receipt of event information. If so, then the process is continued, proceeding with step 1504. If not, then a determination is made in step 1540 whether to end EBC system operations. If not, then the process is continued, proceeding with step 1504. Otherwise EBC system operations are ended in step 1542.
[0245] However, if it was determined in step 1506 that an event was detected, then event enrichment operations, described in greater detail herein, are performed on the event in step 1508. In various embodiments, the event enrichment operations may include certain entity behavior detection operations, described in greater detail herein. Analytic utility detection operations are then performed on the resulting enriched event in step 1510 to identify entity behavior of analytic utility, as likewise described in greater detail herein. A determination is then made in step 1512 to determine whether the enriched event is associated with entity behavior of analytic utility. If not, then the process is continued, proceeding with step 1540. Otherwise, an observable is derived from the event in step 1514, as described in greater detail herein.
[0246] The resulting observable is then processed with associated observables in step 1516 to generate a security related activity, likewise described in greater detail herein. In turn, the resulting security related activity is processed with associated security related activities in step 1518 to generate an activity session, described in greater detail. Thereafter, as described in greater detail herein, the resulting activity session is processed in step 1520 to generate a corresponding activity session. In turn, the resulting activity session is processed with the activity session in step 1522 to generate an EBP element, which is then added to an associated EBP in step 1524
[0247] Thereafter, in step 1526, certain contextualization information stored in a repository of EBC data may be retrieved and then used in step 1528 to perform entity behavior contextualization operations to generate inferences related to the entity's behavior. The EBP is then processed with resulting entity behavior inferences in step 1530 to associate the EBP with one or more corresponding risk use cases, as described in greater detail herein. In turn, the one or more risk use cases are then associated in step 1532 with one or more corresponding security vulnerability scenarios, as likewise described in greater detail herein.
[0248] Then, in step 1534, entity behavior meaning derivation operations are performed on the EBP and each security vulnerability behavior scenario selected in step 1532 to determine whether the entity's behavior warrants performance of a security operation. Once that determination is made, a subsequent determination is made in step 1536 whether to perform a security operation. If not, then the process is continued, proceeding with step 1540. Otherwise, the appropriate security operation, described in greater detail herein, is performed in step 1538 and the process is continued, proceeding with step 1540.
[0249] FIG. 16 shows a functional block diagram of the operation of an entity behavior catalog (EBC) system implemented in accordance with an embodiment of the invention. In various embodiments, certain EBC-related information, described in greater detail herein, may be provided by various EBC data sources 810, likewise described in greater detail herein. In certain embodiments, the EBC data sources 810 may include endpoint devices 304, edge devices 202, third party sources 1606 and other 1620 data sources. In certain embodiments, the receipt of EBC-related information provided by third party sources 1606 may be facilitated through the implementation of one or more Apache NiFi connectors 1608 familiar to skilled practitioners of the art.
[0250] In certain embodiments, activity sessionization and session fingerprint generation 1620 operations may be performed on the EBC-related information provided by the EBC data sources 810 to generate discrete sessions. As used herein, activity sessionization broadly refers to the act of turning event-based data into activity sessions, described in greater detail herein. In these embodiments, the method by which certain EBC-related information is selected to be used in the generation of a particular activity session, and the method by which the activity session is generated, is a matter of design choice. As likewise used herein, an activity session broadly refers to an interval of time during which one or more user or non-user behaviors are respectively enacted by a user or non-user entity.
[0251] In certain embodiments, the user or non-user behaviors enacted during an activity session may be respectively associated with one or more events, described in greater detail herein. In certain embodiments, an activity session may be implemented to determine whether or not user or non-user behaviors enacted during the session are of analytic utility. As an example, certain user or non-user behaviors enacted during a particular activity session may indicate the behaviors were enacted by an impostor. As another example, certain user or non-user behaviors enacted during a particular activity session may be performed by an authenticated entity, but the behaviors may be unexpected or out of the norm.
[0252] In certain embodiments, two or more activity sessions may be contiguous. In certain embodiments, two or more activity sessions may be noncontiguous, but associated. In certain embodiments, an activity session may be associated with two or more other activity sessions. In certain embodiments, an activity session may be a subset of another activity session. In certain embodiments, the interval of time corresponding to a first activity session may overlap an interval of time corresponding to a second activity session. In certain embodiments, an activity session may be associated with two or more other activity sessions whose associated intervals of time may overlap one another. Skilled practitioners of the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope or intent of the invention.
[0253] The resulting activity sessions and session fingerprints are then ingested 1616, followed by the performance of data enrichment 1614 operations familiar to those of skill in the art. In certain embodiments, user identifier information (ID) information provided by a user ID management system 1612 may be used to perform the data enrichment 1614 operations. In various embodiments, certain contextual information related to a particular entity behavior or event may be used to perform the data enrichment 1614 operations. In various embodiments, certain temporal information, such as timestamp information, related to a particular entity behavior or event may be used to perform the data enrichment 1614 operations. In certain embodiments, a repository of EBC data 690 may be implemented to include repositories of entity attribute data 1694, entity behavior data 1695, and behavioral model data 1696. In various embodiments, certain information stored in the repository of entity attribute data 1694 may be used to perform the data enrichment operations 1614.
[0254] In certain embodiments, the data enrichment 1614 operations may include the performance of one or more entity behavior detection 1110 operations, described in greater detail herein. In certain embodiments, the entity behavior detection 1110 operations may be performed by an entity behavior detection system, described in greater detail herein. In various embodiments, certain lexical information stored in a repository of lexicon data 672 may be used to perform the entity behavior detection 1110 operations. In certain embodiments, the data enrichment 1614 operations may be performed without performing any associated entity behavior detection 1110 operations. Those of skill in the art will recognize that many such embodiments are possible. Accordingly, the foregoing is not intended to limit the spirit, scope, or intent of the invention.
[0255] In certain embodiments, the resulting enriched sessions may be stored in the repository of entity behavior data 1695. In certain embodiments, the resulting enriched sessions may be provided to a risk services 422 module, described in greater detail herein. In certain embodiments, as likewise described in greater detail herein, the risk services 422 module may be implemented to generate inferences, risk models, and risk scores, or a combination thereof. In certain embodiments, the resulting inferences, risk models, and risk scores, or a combination thereof, may then be stored in the repository of entity behavioral model data 1696.
[0256] In certain embodiments, the risk services 422 module may be implemented to provide input data associated with the inferences, risk models, and risk scores it may generate to a security policy service 1628. In certain embodiments, the security policy service 1628 may be implemented to use the inferences, risk models, and risk scores to generate security policies. In turn, the security policy service 1628 may be implemented in certain embodiments to export 1630 the resulting security policies to endpoint agents or devices 304, edge devices 202, or other security mechanisms, where they may be used to limit risk, as described in greater detail herein. In certain embodiments, an EBC access management module 1632 may be implemented to provide administrative access to various components of the EBC system 120, as shown in FIG. 16 . In certain embodiments, the EBC access management module 1632 may include a user interface (UI), or a front-end, or both, familiar to skilled practitioners of the art.
[0257] FIGS. 17a and 17b are a simplified block diagram showing reference architecture components of an entity behavior catalog (EBC) system implemented in accordance with an embodiment of the invention for performing certain EBC operations. In various embodiments, the EBC system 120 may be implemented to generate, manage, store, or some combination thereof, information related to the behavior of an associated entity. In certain embodiments, the EBC system 120 may be implemented to provide an inventory of entity behaviors for use when performing a security operation, described in greater detail herein.
[0258] In certain embodiments, an entity behavior catalog (EBC) system 120 may be implemented to identify a security related activity, described in greater detail herein. In certain embodiments, the security related activity may be based upon an observable, likewise described in greater detail herein. In certain embodiments, the observable may include event information corresponding to electronically-observable behavior enacted by an entity. In certain embodiments, the event information corresponding to electronically-observable behavior enacted by an entity may be received from an electronic data source, such as the EBC data sources 810 shown in FIGS. 8, 16, 17 b, and 18. In various embodiments, entity behavior detection operations 1110, described in greater detail herein, may be performed on certain event information received from an EBC data source 810. In certain of these embodiments, the entity behavior detection operations 1110 may include performing event information enrichment operations, likewise described in greater detail herein.
[0259] In certain embodiments, as likewise described in greater detail herein, the EBC system 120 may be implemented to identify a particular event of analytic utility by analyzing an observable associated with a particular security related activity. In certain embodiments, the EBC system 120 may be implemented to generate entity behavior catalog data based upon an identified event of analytic utility. In certain embodiments, an observable 906 may be derived, as described in greater detail herein, from an identified event of analytic utility. In various embodiments, the EBC system 120 may be implemented to associate certain entity behavior data it may generate with a predetermined abstraction level, described in greater detail herein.
[0260] In various embodiments, the EBC system 120 may be implemented to use certain entity behavior catalog data, and an associated abstraction level, to generate a hierarchical set of entity behaviors, described in greater detail herein. In certain embodiments, the hierarchical set of entity behaviors generated by the EBC system 120 may represent an associated security risk, likewise described in greater detail herein. Likewise, as described in greater detail herein, the EBC system 120 may be implemented in certain embodiments to store the hierarchical set of entity behaviors within a repository of EBC data 690.
[0261] In various embodiments, the EBC system 120 may be implemented to receive certain event information, described in greater detail herein, corresponding to an event associated with an entity interaction, likewise described in greater detail herein. In various embodiments, the event information may be generated by, received from, or a combination thereof, certain EBC data sources 810. In certain embodiments, such EBC data sources 810 may include endpoint devices 304, edge devices 202, identity and access 1704 systems familiar to those of skill in the art, as well as various software and data security 1706 applications. In various embodiments, EBC data sources 810 may likewise include output from certain processes 1708, network 1710 access and traffic logs, domain 1712 registrations and associated entities, certain resources 750, described in greater detail herein, event logs 1714 of all kinds, and so forth.
[0262] In certain embodiments, EBC system 120 operations are begun with the receipt of information associated with a particular event. In certain embodiments, information associated with the event may include user entity profile attributes, user behavior factors, user entity mindset factors, entity state information, and contextual information, described in greater detail herein, or a combination thereof. In certain embodiments, the event may be associated with a user/device, a user/network, a user/resource, or a user/user interaction, as described in greater detail herein. In various embodiments, certain user entity profile data, user entity mindset profile data, non-user entity profile data, entity state data, contextual information, and temporal information stored in the repository of EBC data 690 may be retrieved and then used to perform event enrichment operations to enrich the information associated with the event. In certain embodiments, the event enrichment operations may be performed by the event enrichment 680 module.
[0263] In various embodiments, an observable 906, described in greater detail herein, may be derived from the resulting enriched, contextualized event. As shown in FIG. 17b , examples of such observables may include firewall file download 1718, data loss protection (DLP) download 1720, and various operating system (OS) events 1722, 1726, and 1734. As likewise shown in FIG. 17b , other examples of such observables may include cloud access security broker (CASB) events 1724 and 1732, endpoint spawn 1728, insider threat process start 1730, DLP share 1736, and so forth. In certain embodiments, the resulting observables 906 may in turn be respectively associated with a corresponding observable abstraction level, described in greater detail herein.
[0264] In certain embodiments, security related activity abstraction operations, described in greater detail herein, may be performed on the resulting observables 906 to generate a corresponding security related activity 908. In various embodiments, a security related activity 908 may be expressed in a Subject Action Object format and associated with observables 906 resulting from event information received from certain EBC data sources 810. In certain embodiments, a security related activity abstraction operation, described in greater detail herein, may be performed to abstract away EBC data source-specific knowledge and details when expressing an entity behavior. For example, rather than providing the details associated with a “Windows:4624” non-user entity event, the security related activity 908 is abstracted to a “User Login To Device” OS event 1722, 1726, 1734.
[0265] As shown in FIG. 17b , examples of security related activities 908 may include “user downloaded document” 1722, “device spawned process” 1744, “user shared folder” 1746, and so forth. To provide other examples, the security related activity 908 “user downloaded document” 1722 may be associated with observables 906 firewall file download 1718, DLP download 1720, OS event 1722, and CASB event 1724. Likewise, the security related activity 908 “device spawned process” 1744, may be associated with observables 906, OS event 1726, endpoint spawn 1728, and insider threat process start 1730. The security related activity 908 “user shared folder” 1746 may likewise be associated with observables 906 CASB event 1732, OS event 1734, and DLP share 1736.
[0266] In certain embodiments, security related activities 908 may in turn be respectively associated with a corresponding security related activity abstraction level, described in greater detail herein. In various embodiments, activity sessionization operations, likewise described in greater detail herein, may be performed to respectively associate certain events and security related activities 908 with corresponding activity sessions, likewise described in greater detail herein. Likewise, as described in greater detail herein, the resulting session information may be used in various embodiments to associate certain events of analytic utility, or their corresponding observables 906, or their corresponding security related activities 908, or a combination thereof, with a particular activity session.
[0267] In certain embodiments, the resulting security related activities 908 may be processed to generate an associated EBP element 980, as described in greater detail herein. In various embodiments, the EBP element 980 may include user entity attribute 1748 information, non-user entity attribute 1750 information, entity behavior 1752 information, and so forth. In certain of these embodiments, the actual information included in a particular EBP element 980, the method by which it is selected, and the method by which it is associated with the EBP element 980, is a matter of design choice. In certain embodiments, the EBP elements 980 may in turn be respectively associated with a corresponding EBP element abstraction level, described in greater detail herein.
[0268] In various embodiments, certain EBP elements 980 may in turn be associated with a particular EBP 638. In certain embodiments, the EBP 638 may be implemented as a class of user 1762 EBPs, an entity-specific user 1762 EBP, a class of non-user 1766 EBPs, an entity-specific non-user 1768 EBP, and so forth. In certain embodiments, classes of user 1762 and non-user 1766 EBPs may respectively be implemented as a prepopulated EBP, described in greater detail herein. In various embodiments, certain entity data associated with EBP elements 980 associated with the classes of user 1762 and non-user 1766 EBPs may be anonymized. In certain embodiments, the EBP 638 may in turn be associated with an EBP abstraction level, described in greater detail herein.
[0269] In certain embodiments, security risk use case association operations may be performed to associate an EBP 638 with a particular security risk use case 1770. As shown in FIG. 17a examples of such security risk use cases 1770 include “data exfiltration” 1772, “data stockpiling” 1774, “compromised insider” 1776, “malicious user” 1778, and so forth. In various embodiments, entity behavior of analytic utility resulting from the performance of certain analytic utility detection operations may be used identify one or more security risk use cases 1770 associated with a particular EBP 638. In certain embodiments, identified security risk use cases may in turn be associated with a security risk use case abstraction level, described in greater detail herein.
[0270] In certain embodiments, the results of the security risk use case association operations may be used to perform security vulnerability scenario association operations to associate one or more security risk use cases 1770 to one or more security vulnerability scenarios 1780 described in greater detail herein. As shown in FIG. 17a , examples of security vulnerability scenarios 1780 include “accidental disclosure” 1782, “account takeover” 1785, “theft of data” 1786, “sabotage” 1788, “regulatory compliance” 1790, “fraud” 1792, “espionage” 1794, and so forth. To continue the example, the “theft of data” 1786 security vulnerability scenario may be associated with the “data exfiltration” 1772, “data stockpiling” 1774, “compromised insider” 1776, “malicious user” 1778 security risk use cases 1770. Likewise the “sabotage” 1788 and “fraud” 1792 security vulnerability scenarios may be respectively associated with some other security risk case 1770. In certain embodiments, the associated security vulnerability scenarios may in turn be associated with a security vulnerability scenario abstraction level, described in greater detail herein.
[0271] FIG. 18 is a simplified block diagram showing the mapping of entity behaviors to a risk use case scenario implemented in accordance with an embodiment of the invention. In certain embodiments, an entity behavior catalog (EBC) system 120 may be implemented, as described in greater detail herein, to receive event information from a plurality of EBC data sources 810, which is then processed to determine whether a particular event is of analytic utility. In various embodiments, entity behavior detection operations 1110, described in greater detail herein, may be performed on certain event information received from an EBC data source 810. In certain of these embodiments, the entity behavior detection operations 1110 may include performing event information enrichment operations, likewise described in greater detail herein. In various embodiments, performance of the entity behavior operations 1110 may assist in determining whether certain events are of analytical utility.
[0272] In certain embodiments, the EBC system 120 may be implemented to derive observables 906 from identified events of analytic utility, as likewise described in greater detail herein. In certain embodiments, the EBC system 120 may be implemented, as described in greater detail herein, to associate related observables 906 with a particular security related activity 908, which in turn is associated with a corresponding security risk use case 1770. In various embodiments, certain contextual information may be used, as described in greater detail herein, to determine which security related activities 908 may be associated with which security risk use cases 1770.
[0273] In certain embodiments, a single 1860 security related activity 908 may be associated with a particular security risk use case 1770. For example, as shown in FIG. 18 , event data may be received from a Unix/Linux® event log 1812 and a Windows® directory 1804. In this example, certain event data respectively received from the Unix/Linux® event log 1812 and Windows® directory 1804 may be associated with an event of analytic utility, which results in the derivation of observables 906 “File In Log Deleted” 1822 and “Directory Accessed” 1824. To continue the example, the resulting observables 906 “File In Log Deleted” 1822 and “Directory Accessed” 1824 may then be associated with the security related activity 908 “Event Log Cleared” 1844. In turn, the security related activity 908 “Event Log Cleared” 1844 may be associated with security risk use case 1770 “Administrative Evasion” 1858.
[0274] In certain embodiments, two or more 1864 security related activities 908 may be associated with a particular security risk use case 1770. For example, as shown in FIG. 18 , event data may be received from an operating system (OS) 1806 an insider threat 1808 detection system, an endpoint 1810 and a firewall 1812. In this example, certain event data respectively received from the operating system (OS) 1806, an insider threat 1808 detection system, an endpoint 1810 and a firewall 1812 may be associated with an event of analytic utility. Accordingly, observables 906 “Security Event ID” 1826, “New Connection” 1828, may be respectively derived from the event data of analytical utility received from the endpoint 1810 and the firewall 1812 EBC data sources 810. Likewise, observables 906 “Connection Established” 1830 and “Network Scan” 1832 may be respectively derived from the event data of analytical utility received from the OS 1806, the insider threat 1808 detection system, EBC data sources 810.
[0275] To continue the example, the resulting observables 906 “Security Event ID” 1826, “New Connection” 1828 and “Connection Established” 1830 may be associated with security related activity 908 “Device Connected To Port” 1846. Likewise, observable 906 “Network Scan” 1832 may be associated with security related activity 908 “Network Scan” 1848. In turn, the security related activities 908 “Device Connected To Port” 1846 and “Network Scan” 1832 may be associated with security risk use case 1770 “Internal Horizontal Scanning” 1862.
[0276] In certain embodiments, a complex set 1868 of security related activities 908 may be associated with a particular security risk use case 1770. For example, as shown in FIG. 18 , event data may be received from an OS 1814, an internal cloud access security broker (CASB) 1816, an external CASB 1818, and an endpoint 1820. In this example, certain event data respectively received from the OS 1814, the internal cloud access security broker (CASB) 1816, the external CASB 1818, and the endpoint 1820 may be associated with an event of analytic utility.
[0277] Accordingly, observables 906 “OS Event” 1834, “CASB Event” 1840, and “New Application” 1842 may be respectively derived from the event data of analytical utility provided by the OS 1814, the external CASB 1818, and the endpoint 1820 EBC data sources 810. Likewise, a first “CASB Event ID” 1836 observable 906 and a second “CASB Event ID” 1838 observable 906 may both be derived from the event data of analytical utility received from the internal CASB 1816 EBC data source 810
[0278] To continue the example, the “OS Event” 1834, the first “CASB Event ID” 1836, and “New Application” 1842 observables 906 may then be respectively associated with security related activities 908 “New USB Device” 1850, “Private Shareable Link” 1852, and “File Transfer Application” 1856. Likewise, second “CASB Event ID” 1838 observable 906 and the “CASB Event” 1840 observable 906 may then be associated with security related activity 908 “Public Shareable Link” 1854. In turn, the security related activities 908 “New USB Device” 1850, “Private Shareable Link” 1852, “Public Shareable Link” 1854, and “File Transfer Application” 1856 may be associated with security risk use case 1770 “Data Exfiltration Preparations” 1866.
[0279] FIG. 19 is a simplified block diagram of an entity behavior catalog (EBC) system environment implemented in accordance with an embodiment of the invention. In certain embodiments, the EBC system environment may be implemented to detect user or non-user entity behavior of analytic utility and respond to mitigate risk, as described in greater detail herein. In certain embodiments, the EBC system environment may be implemented to include a security analytics system 118, likewise described in greater detail herein. In certain embodiments, the security analytics system 118 may be implemented to include an EBC system 120, an entity behavior detection system 122, or both.
[0280] In certain embodiments, analyses performed by the security analytics system 118 may be used to identify behavior associated with a particular entity that may be of analytic utility. In certain embodiments, as likewise described in greater detail herein, the EBC system 120, or the entity behavior detection system 122, or both, may be used in combination with the security analytics system 118 to perform such analyses. In various embodiments, certain data stored in a repository of security analytics 680 data, a repository of EBC 690 data, or a repository of event 670 data, or a combination thereof, may be used by the security analytics system 118, the EBC system 120, the entity behavior detection system 122, or some combination thereof, to perform the analyses.
[0281] In certain embodiments, the EBC system 120, as described in greater detail herein, may be implemented to use entity behavior information to generate an entity behavior profile (EBP), likewise as described in greater detail herein. In certain embodiments, the security analytics system 118 may be implemented to use one or more session-based fingerprints to perform security analytics operations to detect such user or non-user entity behavior. In certain embodiments, the security analytics system 118 may be implemented to monitor entity behavior associated with a user entity, such as a user ‘A’ 702 or user ‘B’ 772. In certain embodiments, the user or non-user entity behavior may be monitored during user/device 730, user/network 742, user/resource 748, and user/user 770 interactions. In certain embodiments, the user/user 770 interactions may occur between a first user, such as user ‘A’ 702 and user ‘B’ 772.
[0282] In certain embodiments, the entity behavior detection system 122 may be implemented to perform an entity behavior detection operation, described in greater detail herein. In various embodiments, as likewise described in greater detail herein, the behavior detection system 122 may be implemented to use certain lexical information to perform the entity behavior detection operation. In certain embodiments, the lexical information may be stored in a repository of lexicon 672 data. In various embodiments, a lexicon construction system 124 may be implemented to provide certain lexical information stored in the repository of lexicon 672 data to the security analytics system 118 for use by the entity behavior detection system 122.
[0283] In certain embodiments, the lexicon construction system 124 may be implemented, as described in greater detail herein, to construct a lexicon. In various embodiments, as likewise described in greater detail herein, the lexicon construction system 124 may be implemented to learn a lexicon by processing certain event information associated with entity behavior enacted by one or more entities. In certain embodiments, the lexicon construction system 124 may be implemented to store a learned lexicon in the repository of lexicon 672 data.
[0284] In certain embodiments, as described in greater detail herein, an endpoint agent 306 may be implemented on an endpoint device 304 to perform user or non-user entity behavior monitoring. In certain embodiments, the user or non-user entity behavior may be monitored by the endpoint agent 306 during user/device 730 interactions between a user entity, such as user ‘A’ 702, and an endpoint device 304. In certain embodiments, the user or non-user entity behavior may be monitored by the endpoint agent 306 during user/network 742 interactions between user ‘A’ 702 and a network, such as an internal 744 or external 746 network. In certain embodiments, the user or non-user entity behavior may be monitored by the endpoint agent 306 during user/resource 748 interactions between user ‘A’ 702 and a resource 750, such as a facility, printer, surveillance camera, system, datastore, service, and so forth. In certain embodiments, the monitoring of user or non-user entity behavior by the endpoint agent 306 may include the monitoring of electronically-observable actions respectively enacted by a particular user or non-user entity. In certain embodiments, the endpoint agent 306 may be implemented in combination with the security analytics system 118 and the EBC system 120 to detect entity behavior of analytic utility and perform a security operation to mitigate risk.
[0285] In certain embodiments, the endpoint agent 306 may be implemented to include an event analytics 310 module and an EBP feature pack 1908. In certain embodiments, the EBP feature pack 1908 may be further implemented to include an event data detector 1910 module, an entity behavior data detector 1912 module, an event and entity behavior data collection 1914 module, an analytic utility detection 1916 module, an observable derivation 1918 module, and a security related activity abstraction 1920 module, or a combination thereof. In certain embodiments, the event data detector 1910 module may be implemented to detect event data, described in greater detail herein, resulting from user/device 730, user/network 742, user/resource 748, and user/user 770 interactions. In various embodiments, the entity behavior detector 1912 module may be implemented to detect certain user and non-user entity behaviors, described in greater detail herein, resulting from user/device 730, user/network 742, user/resource 748, and user/user 770 interactions.
[0286] In various embodiments, the event and entity behavior data collection 1914 module may be implemented to collect certain event and entity behavior data associated with the user/device 730, user/network 742, user/resource 748, and user/user 770 interactions. In certain embodiments, the analytic utility detection 1916 may be implemented to detect entity behavior of analytic utility associated with events corresponding to the user/device 730, user/network 742, user/resource 748, and user/user 770 interactions. In various embodiments, the observable derivation 1918 module may be implemented to derive observables, described in greater detail herein, associated with events of analytical utility corresponding to the user/device 730, user/network 742, user/resource 748, and user/user 770 interactions. In various embodiments, the security related activity abstraction 1920 module may be implemented to generate a security related activity, likewise described in greater detail herein, from the observables derived by the observable derivation 1916 module.
[0287] In certain embodiments, the endpoint agent 306 may be implemented to communicate the event and entity behavior collected by the event and entity behavior data collector 1914 module, the observables derived by the observable derivation 1916 module, and the security related activities generated by the security related activity abstraction 1918, or a combination thereof, to the security analytics 118 system. In certain embodiments, the security analytics system 118 may be implemented to receive the event and entity behavior data, the observables, and the security related activities provided by the endpoint agent 306. In certain embodiments, the endpoint agent 306 may be implemented to provide the event and entity behavior data, the observables, and the security related activities, or a combination thereof, to the security analytics system 118. In turn, in certain embodiments, the security analytics system 118 may be implemented in certain embodiments to provide the event and entity behavior data, the observables, and the security related activities, or a combination thereof, to the EBC system 120 for processing.
[0288] In certain embodiment, the EBC system 120 may be implemented to include an entity behavior contextualization 1980 module, an EBP session generator 1982 module, an EBP element generator 1984, or a combination thereof. In certain embodiments, the EBP element generator 1982 module may be implemented to process the event and entity behavior data, the observables, and the security related activities provided by the endpoint agent 306 to generate EBP elements, described in greater detail herein. In certain embodiments, the EBP session generator 1984 may be implemented to use the event and entity behavior data, the observables, and the security related activities provided by the endpoint agent 306, to generate session information. In certain embodiments, the EBP session generator 1984 may be implemented to use the resulting session information to generate an activity session, described in greater detail herein. In various embodiments, as likewise described in greater detail herein, certain EBP management operations may be performed to associate EBP elements generated by the EBP element generator 1982 module with a corresponding EBP. Likewise, certain EBP management operations may be performed to use the session information generated by the EBP session generator 1984 module to associate a particular EBP element with a particular EBP
[0289] In certain embodiments, the EBC system 120 may be implemented as a distributed system. Accordingly, various embodiments of the invention reflect an appreciation that certain modules, or associated functionalities, may be implemented either within the EBC system 120 itself, the EBP feature pack 1908, an edge device 202, an internal 744 or external 746 network, an external system 780, or some combination thereof. As an example, the functionality provided, and operations performed, by the analytic utility detection 1916, observable derivation 1918 and security related activity abstraction 1920 modules may be implemented within the EBC system 120 in certain embodiments. Likewise, the functionality provided, and operations performed, by the entity behavior contextualization 1980, EBP session generator 1982, and EBP element generator 1984 may be implemented within the EBP feature pack 1908. Those of skill in the art will recognize that many such implementations are possible. Accordingly, the foregoing is not intended to limit the spirit, scope, or intent of the invention.
[0290] As will be appreciated by one skilled in the art, the present invention may be embodied as a method, system, or computer program product. Accordingly, embodiments of the invention may be implemented entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in an embodiment combining software and hardware. These various embodiments may all generally be referred to herein as a “circuit,” “module,” or “system.” Furthermore, the present invention may take the form of a computer program product on a computer-usable storage medium having computer-usable program code embodied in the medium.
[0291] Any suitable computer usable or computer readable medium may be utilized. The computer-usable or computer-readable medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, or a magnetic storage device. In the context of this document, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[0292] Computer program code for carrying out operations of the present invention may be written in an object oriented programming language such as Java, Smalltalk, C++ or the like. However, the computer program code for carrying out operations of the present invention may also be written in conventional procedural programming languages, such as the “C” programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).
[0293] Embodiments of the invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
[0294] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.
[0295] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
[0296] The present invention is well adapted to attain the advantages mentioned as well as others inherent therein. While the present invention has been depicted, described, and is defined by reference to particular embodiments of the invention, such references do not imply a limitation on the invention, and no such limitation is to be inferred. The invention is capable of considerable modification, alteration, and equivalents in form and function, as will occur to those ordinarily skilled in the pertinent arts. The depicted and described embodiments are examples only, and are not exhaustive of the scope of the invention.
[0297] Consequently, the invention is intended to be limited only by the spirit and scope of the appended claims, giving full cognizance to equivalents in all respects.
Claims
What is claimed is:
1. A computer-implementable method for constructing a lexicon, comprising:
identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term;
grouping terms from the plurality of training events into topic clusters;
analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters;
deriving a plurality of learned lexicons from the plurality of classified clusters;
storing the plurality of learned lexicons in a repository of lexicon data; and,
performing a security operation via a security analytics system, the security analytics system executing on a hardware processor of an information handling system, the security operation using the plurality of learned lexicons to perform an entity behavior detection operation.
3. The method of claim 1, further comprising:
receiving a stream of events, the stream of events comprising a plurality of monitored events;
performing an entity behavior detection operation, the entity behavior detection operation classifying the plurality of events using the plurality of learned lexicons.
4. The method of claim 3, further comprising:
performing a security analytics operation on the plurality of events, the security analytics operation analyzing terms contained within the plurality of events based upon the plurality of learned lexicons.
5. The method of claim 3, further comprising:
providing the plurality of classified events as additional training events to tune the learned lexicons.
6. The method of claim 1, wherein:
the grouping of terms from the plurality of training events into topic clusters is performed via a topic mapping operation.
7. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term;
grouping terms from the plurality of training events into topic clusters;
analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters;
deriving a plurality of learned lexicons from the plurality of classified clusters;
storing the plurality of learned lexicons in a repository of lexicon data; and,
performing a security operation via a security analytics system, the security analytics system executing on the processor, the security operation using the plurality of learned lexicons to perform an entity behavior detection operation.
9. The system of claim 7, wherein the instructions are further configured for:
receiving a stream of events, the stream of events comprising a plurality of monitored events;
performing an entity behavior detection operation, the entity behavior detection operation classifying the plurality of events using the plurality of learned lexicons.
10. The system of claim 9, wherein the instructions are further configured for:
performing a security analytics operation on the plurality of events, the security analytics operation analyzing terms contained within the plurality of events based upon the plurality of learned lexicons.
11. The system of claim 9, wherein the instructions are further configured for:
providing the plurality of classified events as additional training events to tune the learned lexicons.
12. The system of claim 7, wherein:
the grouping of terms from the plurality of training events into topic clusters is performed via a topic mapping operation.
13. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term;
grouping terms from the plurality of training events into topic clusters;
analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters;
deriving a plurality of learned lexicons from the plurality of classified clusters;
storing the plurality of learned lexicons in a repository of lexicon data; and,
performing a security operation via a security analytics system, the security analytics system executing on a hardware processor of an information handling system, the security operation using the plurality of learned lexicons to perform an entity behavior detection operation.
14. The non-transitory, computer-readable storage medium of claim 13, wherein:
an event of the plurality of event comprises unstructured data.
15. The non-transitory, computer-readable storage medium of claim 13, wherein the computer executable instructions are further configured for:
receiving a stream of events, the stream of events comprising a plurality of monitored events;
performing an entity behavior detection operation, the entity behavior detection operation classifying the plurality of events using the plurality of learned lexicons.
16. The non-transitory, computer-readable storage medium of claim 15, wherein the computer executable instructions are further configured for:
performing a security analytics operation on the plurality of events, the security analytics operation analyzing terms contained within the plurality of events based upon the plurality of learned lexicons.
17. The non-transitory, computer-readable storage medium of claim 15, wherein the computer executable instructions are further configured for:
providing the plurality of classified events as additional training events to tune the learned lexicons.
18. The non-transitory, computer-readable storage medium of claim 13, wherein:
the grouping of terms from the plurality of training events into topic clusters is performed via a topic mapping operation.
19. The non-transitory, computer-readable storage medium of claim 13, wherein the computer executable instructions are deployable to a client system from a server system at a remote location.
20. The non-transitory, computer-readable storage medium of claim 13, wherein the computer executable instructions are provided by a service provider to a user on an on-demand basis.
Patent Citations (272)
| Patent | Date | Inventor | Cited By |
|---|---|---|---|
| US6072875(A) | 2000-06-01 | Tsudik | Applicant |
| US6678693(B1) | 2004-01-01 | Shiraishi | Applicant |
| US7107447(B2) | 2006-09-01 | Sanin et al. | Applicant |
| US7694150(B1) | 2010-04-01 | Kirby | Applicant |
| US7725565(B2) | 2010-05-01 | Li et al. | Applicant |
| US7813944(B1) | 2010-10-01 | Luk et al. | Applicant |
| US7933960(B2) | 2011-04-01 | Chen et al. | Applicant |
| US8181253(B1) | 2012-05-01 | Zaitsev et al. | Applicant |
| US8312064(B1) | 2012-11-01 | Gauvin | Applicant |
| US8424061(B2) | 2013-04-01 | Rosenoer | Applicant |
| US8484066(B2) | 2013-07-01 | Miller et al. | Applicant |
| US8490163(B1) | 2013-07-01 | Harsell et al. | Applicant |
| US8713633(B2) | 2014-04-01 | Thomas | Applicant |
| US8776168(B1) | 2014-07-01 | Gibson et al. | Applicant |
| US8826443(B1) | 2014-09-01 | Raman et al. | Applicant |
| US8892690(B2) | 2014-11-01 | Liu et al. | Applicant |
| US8990930(B2) | 2015-03-01 | Burrell et al. | Applicant |
| US9015812(B2) | 2015-04-01 | Plattner et al. | Applicant |
| US9015847(B1) | 2015-04-01 | Kaplan et al. | Applicant |
| US9043905(B1) | 2015-05-01 | Allen et al. | Applicant |
| US9053124(B1) | 2015-06-01 | Dornquast et al. | Applicant |
| US9128995(B1) | 2015-09-01 | Fletcher et al. | Applicant |
| US9137318(B2) | 2015-09-01 | Hong | Applicant |
| US9166999(B1) | 2015-10-01 | Kulkarni et al. | Applicant |
| US9223972(B1) | 2015-12-01 | Vincent et al. | Applicant |
| US9246941(B1) | 2016-01-01 | Gibson et al. | Applicant |
| US9262722(B1) | 2016-02-01 | Daniel | Applicant |
| US9298726(B1) | 2016-03-01 | Mondal et al. | Applicant |
| US9342553(B1) | 2016-05-01 | Fuller | Applicant |
| US9369433(B1) | 2016-06-01 | Paul et al. | Applicant |
| US9378065(B2) | 2016-06-01 | Shear | Examiner |
| US9485266(B2) | 2016-11-01 | Baxley et al. | Applicant |
| US9542650(B2) | 2017-01-01 | Lospinoso et al. | Applicant |
| US9596146(B2) | 2017-03-01 | Coates et al. | Applicant |
| US9609010(B2) | 2017-03-01 | Sipple | Applicant |
| US9665854(B1) | 2017-05-01 | Burger et al. | Applicant |
| US9672279(B1) | 2017-06-01 | Cohen | Examiner |
| US9692762(B2) | 2017-06-01 | Barkan et al. | Applicant |
| US9755913(B2) | 2017-09-01 | Bhide et al. | Applicant |
| US9762582(B1) | 2017-09-01 | Hockings et al. | Applicant |
| US9798883(B1) | 2017-10-01 | Gil et al. | Applicant |
| US9904579(B2) | 2018-02-01 | Shear | Examiner |
| US9935891(B1) | 2018-04-01 | Stamos | Applicant |
| US9977824(B2) | 2018-05-01 | Agarwal et al. | Applicant |
| US10075384(B2) | 2018-09-01 | Shear | Examiner |
| US10096065(B2) | 2018-10-01 | Little | Applicant |
| US10108544(B1) | 2018-10-01 | Duggal et al. | Applicant |
| US10187369(B2) | 2019-01-01 | Caldera et al. | Applicant |
| US10210283(B2) | 2019-02-01 | Broz et al. | Applicant |
| US10235285(B1) | 2019-03-01 | Wallace | Applicant |
| US10237298(B1) | 2019-03-01 | Nguyen et al. | Applicant |
| US10270794(B1) | 2019-04-01 | Mukerji et al. | Applicant |
| US10275671(B1) | 2019-04-01 | Newman | Applicant |
| US10282702(B2) | 2019-05-01 | Paltenghe et al. | Applicant |
| US10284601(B1) | 2019-05-01 | Bar-Menachem et al. | Applicant |
| US10320813(B1) | 2019-06-01 | Ahmed et al. | Applicant |
| US10341391(B1) | 2019-07-01 | Pandey et al. | Applicant |
| US10417454(B1) | 2019-09-01 | Marom et al. | Applicant |
| US10417653(B2) | 2019-09-01 | Milton et al. | Applicant |
| US10419428(B2) | 2019-09-01 | Tunnell et al. | Applicant |
| US10432669(B1) | 2019-10-01 | Badhwar et al. | Applicant |
| US10545738(B1) | 2020-01-01 | Jaeger et al. | Applicant |
| US10579281(B2) | 2020-03-01 | Cherubini et al. | Applicant |
| US10673814(B1) | 2020-06-01 | Huffner | Examiner |
| US10713934(B2) | 2020-07-01 | Sayavong et al. | Applicant |
| US10769908(B1) | 2020-09-01 | Burris et al. | Applicant |
| US10917319(B2) | 2021-02-01 | Scheib et al. | Applicant |
| US11061874(B1) | 2021-07-01 | Funk et al. | Applicant |
| US11366859(B2) | 2022-06-01 | Stevens | Examiner |
| US20020112015(A1) | 2002-08-01 | Haynes | Applicant |
| US20020123865(A1) | 2002-09-01 | Whitney et al. | Applicant |
| US20040034582(A1) | 2004-02-01 | Gilliam et al. | Applicant |
| US20040044613(A1) | 2004-03-01 | Murakami et al. | Applicant |
| US20050120025(A1) | 2005-06-01 | Rodriguez et al. | Applicant |
| US20050198099(A1) | 2005-09-01 | Motsinger et al. | Applicant |
| US20050273850(A1) | 2005-12-01 | Freund | Applicant |
| US20060048209(A1) | 2006-03-01 | Shelest et al. | Applicant |
| US20060053476(A1) | 2006-03-01 | Bezilla et al. | Applicant |
| US20060112111(A1) | 2006-05-01 | Tseng et al. | Applicant |
| US20060117172(A1) | 2006-06-01 | Zhang et al. | Applicant |
| US20060129382(A1) | 2006-06-01 | Anand et al. | Applicant |
| US20060195905(A1) | 2006-08-01 | Fudge | Applicant |
| US20060206449(A1) | 2006-09-01 | Fletcher et al. | Applicant |
| US20060225124(A1) | 2006-10-01 | Kolawa et al. | Applicant |
| US20070043703(A1) | 2007-02-01 | Bhattacharya et al. | Applicant |
| US20070121522(A1) | 2007-05-01 | Carter | Applicant |
| US20070225995(A1) | 2007-09-01 | Moore | Applicant |
| US20070234409(A1) | 2007-10-01 | Eisen | Applicant |
| US20080010274(A1) | 2008-01-01 | Carus | Examiner |
| US20080091670(A1) | 2008-04-01 | Ismalon | Examiner |
| US20080168002(A1) | 2008-07-01 | Kagarlis et al. | Applicant |
| US20080168135(A1) | 2008-07-01 | Redlich et al. | Applicant |
| US20080168453(A1) | 2008-07-01 | Hutson et al. | Applicant |
| US20080198453(A1) | 2008-08-01 | LaFontaine et al. | Applicant |
| US20080244741(A1) | 2008-10-01 | Gustafson et al. | Applicant |
| US20090006888(A1) | 2009-01-01 | Bernhard et al. | Applicant |
| US20090119261(A1) | 2009-05-01 | Ismalon | Examiner |
| US20090177979(A1) | 2009-07-01 | Garbow et al. | Applicant |
| US20090182872(A1) | 2009-07-01 | Hong | Applicant |
| US20090228474(A1) | 2009-09-01 | Chiu et al. | Applicant |
| US20090300712(A1) | 2009-12-01 | Kaufmann et al. | Applicant |
| US20100024014(A1) | 2010-01-01 | Kailash et al. | Applicant |
| US20100049770(A1) | 2010-02-01 | Ismalon | Examiner |
| US20100057662(A1) | 2010-03-01 | Collier et al. | Applicant |
| US20100058016(A1) | 2010-03-01 | Nikara et al. | Applicant |
| US20100094767(A1) | 2010-04-01 | Miltonberger | Applicant |
| US20100094818(A1) | 2010-04-01 | Farrell et al. | Applicant |
| US20100107255(A1) | 2010-04-01 | Eiland et al. | Applicant |
| US20100131507(A1) | 2010-05-01 | Pradhan | Examiner |
| US20100146622(A1) | 2010-06-01 | Nordstrom et al. | Applicant |
| US20100205224(A1) | 2010-08-01 | Palanisamy et al. | Applicant |
| US20100228656(A1) | 2010-09-01 | Wasserblat et al. | Applicant |
| US20100235495(A1) | 2010-09-01 | Petersen et al. | Applicant |
| US20100275263(A1) | 2010-10-01 | Bennett et al. | Applicant |
| US20110035403(A1) | 2011-02-01 | Ismalon | Examiner |
| US20110061093(A1) | 2011-03-01 | Korkus et al. | Applicant |
| US20110167105(A1) | 2011-07-01 | Ramakrishnan et al. | Applicant |
| US20110258049(A1) | 2011-10-01 | Ramer | Examiner |
| US20110307957(A1) | 2011-12-01 | Barcelo et al. | Applicant |
| US20120046989(A1) | 2012-02-01 | Baikalov et al. | Applicant |
| US20120047575(A1) | 2012-02-01 | Baikalov et al. | Applicant |
| US20120079107(A1) | 2012-03-01 | Williams et al. | Applicant |
| US20120110087(A1) | 2012-05-01 | Culver et al. | Applicant |
| US20120137367(A1) | 2012-05-01 | Dupont et al. | Applicant |
| US20120210158(A1) | 2012-08-01 | Akiyama et al. | Applicant |
| US20120259807(A1) | 2012-10-01 | Dymetman | Applicant |
| US20120290215(A1) | 2012-11-01 | Adler et al. | Applicant |
| US20130013550(A1) | 2013-01-01 | Kerby | Applicant |
| US20130054433(A1) | 2013-02-01 | Giard et al. | Applicant |
| US20130055367(A1) | 2013-02-01 | Kshirsagar et al. | Applicant |
| US20130081141(A1) | 2013-03-01 | Anurag | Applicant |
| US20130097662(A1) | 2013-04-01 | Pearcy et al. | Applicant |
| US20130102283(A1) | 2013-04-01 | Lau et al. | Applicant |
| US20130104236(A1) | 2013-04-01 | Ray et al. | Applicant |
| US20130132551(A1) | 2013-05-01 | Bose et al. | Applicant |
| US20130174259(A1) | 2013-07-01 | Pearcy et al. | Applicant |
| US20130205366(A1) | 2013-08-01 | Luna et al. | Applicant |
| US20130238422(A1) | 2013-09-01 | Saldanha | Applicant |
| US20130290598(A1) | 2013-10-01 | Fiske et al. | Applicant |
| US20130297729(A1) | 2013-11-01 | Suni et al. | Applicant |
| US20130305358(A1) | 2013-11-01 | Gathala et al. | Applicant |
| US20130317808(A1) | 2013-11-01 | Kruel et al. | Applicant |
| US20130320212(A1) | 2013-12-01 | Valentino et al. | Applicant |
| US20130340035(A1) | 2013-12-01 | Uziel et al. | Applicant |
| US20140075004(A1) | 2014-03-01 | Van Dusen et al. | Applicant |
| US20140096215(A1) | 2014-04-01 | Hessler | Applicant |
| US20140173727(A1) | 2014-06-01 | Lingafelt et al. | Applicant |
| US20140199663(A1) | 2014-07-01 | Sadeh-Koniecpol et al. | Applicant |
| US20140205099(A1) | 2014-07-01 | Christodorescu et al. | Applicant |
| US20140214938(A1) | 2014-07-01 | Bhatt et al. | Applicant |
| US20140283075(A1) | 2014-09-01 | Drissel et al. | Applicant |
| US20140325634(A1) | 2014-10-01 | Iekel-Johnson et al. | Applicant |
| US20140356445(A1) | 2014-12-01 | Little | Applicant |
| US20150082430(A1) | 2015-03-01 | Sridhara et al. | Applicant |
| US20150113646(A1) | 2015-04-01 | Lee et al. | Applicant |
| US20150154263(A1) | 2015-06-01 | Boddhu et al. | Applicant |
| US20150161386(A1) | 2015-06-01 | Gupta et al. | Applicant |
| US20150199511(A1) | 2015-07-01 | Faile, Jr. et al. | Applicant |
| US20150199629(A1) | 2015-07-01 | Faile, Jr. et al. | Applicant |
| US20150205954(A1) | 2015-07-01 | Jou et al. | Applicant |
| US20150215325(A1) | 2015-07-01 | Ogawa | Applicant |
| US20150220625(A1) | 2015-08-01 | Cartmell et al. | Applicant |
| US20150248476(A1) | 2015-09-01 | Weissinger | Examiner |
| US20150256550(A1) | 2015-09-01 | Taylor et al. | Applicant |
| US20150269383(A1) | 2015-09-01 | Lang et al. | Applicant |
| US20150286819(A1) | 2015-10-01 | Coden et al. | Applicant |
| US20150288709(A1) | 2015-10-01 | Singhal et al. | Applicant |
| US20150324559(A1) | 2015-11-01 | Boss et al. | Applicant |
| US20150324563(A1) | 2015-11-01 | Deutschmann et al. | Applicant |
| US20150326613(A1) | 2015-11-01 | Devarajan et al. | Applicant |
| US20150350902(A1) | 2015-12-01 | Baxley et al. | Applicant |
| US20150356488(A1) | 2015-12-01 | Eden et al. | Applicant |
| US20160021117(A1) | 2016-01-01 | Harmon et al. | Applicant |
| US20160036844(A1) | 2016-02-01 | Kopp et al. | Applicant |
| US20160078362(A1) | 2016-03-01 | Christodorescu et al. | Applicant |
| US20160092774(A1) | 2016-03-01 | Wang et al. | Applicant |
| US20160105334(A1) | 2016-04-01 | Boe et al. | Applicant |
| US20160117937(A1) | 2016-04-01 | Penders et al. | Applicant |
| US20160147380(A1) | 2016-05-01 | Coates et al. | Applicant |
| US20160164922(A1) | 2016-06-01 | Boss et al. | Applicant |
| US20160224803(A1) | 2016-08-01 | Frank et al. | Applicant |
| US20160226914(A1) | 2016-08-01 | Doddy et al. | Applicant |
| US20160232353(A1) | 2016-08-01 | Gupta et al. | Applicant |
| US20160247158(A1) | 2016-08-01 | Kolotinsky | Applicant |
| US20160261621(A1) | 2016-09-01 | Srivastava et al. | Applicant |
| US20160277360(A1) | 2016-09-01 | Dwyier et al. | Applicant |
| US20160277435(A1) | 2016-09-01 | Salajegheh et al. | Applicant |
| US20160286244(A1) | 2016-09-01 | Chang et al. | Applicant |
| US20160300049(A1) | 2016-10-01 | Guedalia et al. | Applicant |
| US20160308890(A1) | 2016-10-01 | Weilbacher | Applicant |
| US20160330219(A1) | 2016-11-01 | Hasan | Applicant |
| US20160330746(A1) | 2016-11-01 | Mehrabanzad et al. | Applicant |
| US20160335865(A1) | 2016-11-01 | Sayavong et al. | Applicant |
| US20160371489(A1) | 2016-12-01 | Puri et al. | Applicant |
| US20170032274(A1) | 2017-02-01 | Yu et al. | Applicant |
| US20170053280(A1) | 2017-02-01 | Lishok et al. | Applicant |
| US20170063888(A1) | 2017-03-01 | Muddu et al. | Applicant |
| US20170070521(A1) | 2017-03-01 | Bailey et al. | Applicant |
| US20170104790(A1) | 2017-04-01 | Meyers et al. | Applicant |
| US20170116054(A1) | 2017-04-01 | Boddhu et al. | Applicant |
| US20170155669(A1) | 2017-06-01 | Sudo et al. | Applicant |
| US20170171609(A1) | 2017-06-01 | Koh | Applicant |
| US20170230418(A1) | 2017-08-01 | Amar et al. | Applicant |
| US20170255536(A1) | 2017-09-01 | Weissinger | Examiner |
| US20170255938(A1) | 2017-09-01 | Biegun et al. | Applicant |
| US20170279616(A1) | 2017-09-01 | Loeb et al. | Applicant |
| US20170286671(A1) | 2017-10-01 | Chari et al. | Applicant |
| US20170331828(A1) | 2017-11-01 | Caldera et al. | Applicant |
| US20170149815(A1) | 2017-12-01 | Bolgert | Applicant |
| US20180004948(A1) | 2018-01-01 | Martin et al. | Applicant |
| US20180007069(A1) | 2018-01-01 | Hunt et al. | Applicant |
| US20180018456(A1) | 2018-01-01 | Chen et al. | Applicant |
| US20180024901(A1) | 2018-01-01 | Tankersley et al. | Applicant |
| US20180025273(A1) | 2018-01-01 | Jordan et al. | Applicant |
| US20180027006(A1) | 2018-01-01 | Zimmermann et al. | Applicant |
| US20180081661(A1) | 2018-03-01 | Gonzalez del Solar et al. | Applicant |
| US20180082307(A1) | 2018-03-01 | Ochs et al. | Applicant |
| US20180091520(A1) | 2018-03-01 | Camenisch et al. | Applicant |
| US20180107528(A1) | 2018-04-01 | Vizer et al. | Applicant |
| US20180121514(A1) | 2018-05-01 | Reisz et al. | Applicant |
| US20180139227(A1) | 2018-05-01 | Martin et al. | Applicant |
| US20180145995(A1) | 2018-05-01 | Roeh et al. | Applicant |
| US20180150570(A1) | 2018-05-01 | Broyd et al. | Applicant |
| US20180191745(A1) | 2018-07-01 | Moradi et al. | Applicant |
| US20180191766(A1) | 2018-07-01 | Holeman et al. | Applicant |
| US20180191857(A1) | 2018-07-01 | Schooler et al. | Applicant |
| US20180204215(A1) | 2018-07-01 | Hu et al. | Applicant |
| US20180232111(A1) | 2018-08-01 | Jones et al. | Applicant |
| US20180232426(A1) | 2018-08-01 | Gomez et al. | Applicant |
| US20180234434(A1) | 2018-08-01 | Viljoen | Applicant |
| US20180248863(A1) | 2018-08-01 | Kao et al. | Applicant |
| US20180276541(A1) | 2018-09-01 | Studnitzer et al. | Applicant |
| US20180285363(A1) | 2018-10-01 | Dennis et al. | Applicant |
| US20180288063(A1) | 2018-10-01 | Koottayi et al. | Applicant |
| US20180295141(A1) | 2018-10-01 | Solotorevsky | Applicant |
| US20180332062(A1) | 2018-11-01 | Ford | Applicant |
| US20180336353(A1) | 2018-11-01 | Manadhata et al. | Applicant |
| US20180341758(A1) | 2018-11-01 | Park et al. | Applicant |
| US20180341889(A1) | 2018-11-01 | Psalmonds et al. | Applicant |
| US20180349221(A1) | 2018-12-01 | Harutyunyan et al. | Applicant |
| US20180349684(A1) | 2018-12-01 | Bapat et al. | Applicant |
| US20190014153(A1) | 2019-01-01 | Lang et al. | Applicant |
| US20190034625(A1) | 2019-01-01 | Ford et al. | Applicant |
| US20190034813(A1) | 2019-01-01 | Das et al. | Applicant |
| US20190036969(A1) | 2019-01-01 | Swafford et al. | Applicant |
| US20190052660(A1) | 2019-02-01 | Cassidy et al. | Applicant |
| US20190095478(A1) | 2019-03-01 | Tankersley et al. | Applicant |
| US20190158503(A1) | 2019-05-01 | Bansal et al. | Applicant |
| US20190174319(A1) | 2019-06-01 | Backholm et al. | Applicant |
| US20190222603(A1) | 2019-07-01 | Yang | Applicant |
| US20190289021(A1) | 2019-09-01 | Ford | Applicant |
| US20190294482(A1) | 2019-09-01 | Li et al. | Applicant |
| US20190311105(A1) | 2019-10-01 | Beiter et al. | Applicant |
| US20190354703(A1) | 2019-11-01 | Ford | Applicant |
| US20190356688(A1) | 2019-11-01 | Ford | Applicant |
| US20190356699(A1) | 2019-11-01 | Ford | Applicant |
| US20190387002(A1) | 2019-12-01 | Ford et al. | Applicant |
| US20190387003(A1) | 2019-12-01 | Ford et al. | Applicant |
| US20190392419(A1) | 2019-12-01 | DeLuca et al. | Applicant |
| US20200034462(A1) | 2020-01-01 | Narayanaswamy et al. | Applicant |
| US20200036740(A1) | 2020-01-01 | Ford | Applicant |
| US20200065728(A1) | 2020-02-01 | Wilson et al. | Applicant |
| US20200077265(A1) | 2020-03-01 | Singh et al. | Applicant |
| US20200089692(A1) | 2020-03-01 | Tripathi et al. | Applicant |
| US20200117546(A1) | 2020-04-01 | Wong et al. | Applicant |
| US20200334025(A1) | 2020-10-01 | Wang et al. | Applicant |
| US20200409951(A1) | 2020-12-01 | Kowolenko | Examiner |
| US20210326527(A1) | 2021-10-01 | Poirel | Examiner |
| US20210357648(A1) | 2021-11-01 | Metaxas | Examiner |
| CN107633044(A) | 2018-01-01 | Examiner | |
| WO2019153581(A1) | 2019-08-01 | Applicant | |
| WO-2019153581(A1) | 2019-08-01 | Applicant |
Non-Patent Literature (25)
- L. F. Lafuerza et al., Exact Solution of a Stochastic Protein Dynamics Model with Delayed Degradation, Phys. Rev. E 84, 051121, Nov. 18, 2011, pp. 1-8.Applicant
- Zoubin Ghahramani, Bayesian nonparametrics and the probabilistic approach to modelling, Philosophical Transactions A of the Royal Society, vol. 371 Issue: 1984, Published Dec. 31, 2012, pp. 1-20.Applicant
- Elena Zheleva et al., Higher-order Graphical Models for Classification in Social and Affiliation Networks, NIPS 2010 Workshop on Networks Across Disciplines: Theory and Applications, Whistler BC, Canada, 2010, pp. 1-7.Applicant
- Varun Chandola et al., Anomaly Detection: A Survey, ACM Computing Surveys, vol. 41, No. 3, Article 15, Jul. 2009, pp. 15.1-58.1.Applicant
- Judea Pearl, The Causal Foundations of Structural Equation Modeling, Technical Report R-370, Computer Science Department, University of California, Los Angeles, also Chapter 5, R. H. Hoyle (Ed.), Handbook of Structural Equation Modeling, New York, Guilford Press, Jun. 4, 2012, pp. 68-91.Applicant
- Yueh-Hsuan Chiang, Towards Large-Scale Temporal Entity Matching, Dissertation Abstract, University of Wisconsin-Madison, 2013.Applicant
- Furong Li, Linking Temporal Records for Profiling Entities, 2015, SIGMOD '15 Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, pp. 593-605, https://users.soe.ucsc.edu/˜tan/papers/2015/modf445-li.pdf.Applicant
- Peter Christen et al., Adaptive Temporal Entity Resolution on Dynamic Databases, Apr. 2013, http://users.cecs.anu.edu.au/˜Peter.Christen/publications/christen2013pakdd-slides.pdf.Applicant
- Wikipedia, Categorical Distribution, edited Jul. 28, 2018, https://en.wikipedia.org/wiki/Categorical_distribution.Applicant
- Wikipedia, One-Hot, edited May 22, 2018, https://en.wikipedia.org/wiki/One-hot.Applicant
- Marinescu, Dan C., Cloud Computing and Computer Clouds, University of Central Florida, 2012, pp. 1-246.Applicant
- Sanjeev Goyal et al., Attack, Defence and Contagion in Networks, The Review of Economic Studies, vol. 81, Issue 4, Oct. 2014, pp. 1518-1542, https://doi.org/10.1093/restud/rdu013 (2014).Applicant
- Singh et al., Container-Based Microservice Architecture for Cloud Applications, International Conference on Computing, Communication and Automation (ICCCA2017), 2017.Applicant
- Barrere et al., Vulnerability Assessment in Autonomic Networks and Services: A Survey, IEEE, Aug. 30, 2013 vol. 16, issue. 2, pp. 988-1004.Applicant
- Burns et al., Automatic Management of Network Security Policy, IEEE, Jun. 14, 2001, pp. 12-26.Applicant
- S. Chambi et al., Better bitmap performance with Roaring bitmaps, arXiv:1402.6407v10 [cs.DB] (Mar. 15, 2016).Applicant
- Jianguo Wang et al., An Experimental Study of Bitmap Compression vs. Inverted List Compression, SIGMOD 2017: Proceedings of the 2017 ACM Int'l Conf. on Management of Data, pp. 993-1008 (May 2017).Applicant
- Sean Barnum, Standardized Cyber Threat Intelligence Information with the Structured Threat Information eXpression (STIX) Whitepaper v1.1 (Feb. 20, 2014).Applicant
- Xiang Sun et al., Event Detection in Social Media Data Streams, IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Automatic and Secure Computing Persuasive Intelligence and Computing, pp. 1711-1717, Dec. 2015.Applicant
- Mesaros et al., Latent Semantic Analysis in Sound Event Detection, 19th European Signal Processing Conference (EUSIPCO 2011), pp. 1307-1311, 2011.Applicant
- Crandall et al., Inferring Social Ties from Geographic Coincidences, PNAS, vol. 107, No. 52, 2010, pp. 22436-22441, 2010.Applicant
- Ross et al., Bully Prevention in Positive Behavior Support, Journal of Applied Behavior Analysis, 42(4), pp. 747-759, 2009.Applicant
- Matt Klein, How to Erase Your iOS Device After Too Many Failed Passcode Attempts, https://www.howtogeek.com/264369/ how-to-erase-your-ios-device-after-too-many-failed-passcode-attempts/, Jul. 28, 2016.Applicant
- Github, The Z3 Theorem Prover, retrieved from internet May 19, 2020, https://github.com/Z3Prover/z3.Applicant
- John Backes et al., Semantic-based Automated Reasoning for AWS Access Policies using SMT, 2018 Formal Methods in Computer Aided Design (FMCAD), Oct. 30-Nov. 2, 2018 https://d1.awsstatic.com/Security/pdfs/Semantic_Based_Automated_Reasoning_for_AWS_Access_Policies_Using_SMT.pdf.Applicant