Entity group behavior profiling

Patent metadata

Field	Value
Publication number	US-10212176-B2
Application number	US-201514743861-A
Country	US
Kind code	B2
Filing date	Jun 18, 2015
Priority date	Jun 23, 2014
Publication date	Feb 19, 2019
Grant date	Feb 19, 2019

Abstract

Entity group behavior profiling. An entity group is created that includes multiple entities, where each entity represents one of a user, a machine, and a service. A behavior profile is created for each one of the entities of the entity group. The behavior of each of one of the entities of the entity group is monitored to detect behavior change. An indicator of compromise is detected based on multiple ones of the entities experiencing substantially a same behavior change.

First claim

What is claimed is:

1. A method, comprising:
creating, by a multi-tier security framework, an entity group that includes a plurality of entities, wherein each one of the plurality of entities represents one of a user, a machine, or a service;
creating, by the multi-tier security framework, a behavior profile for each one of the plurality of entities of the entity group, wherein each behavior profile includes one or more features;
monitoring behavior of each one of the plurality of entities of the entity group by the multi-tier security framework to detect behavior change;
detecting, by a local data engine, an indicator of compromise based on each of the plurality of entities experiencing substantially a same behavior change, the indicator of compromise identifying that a potential threat is directed toward a network including the plurality of entities;
responsive to detecting the indicator of compromise based on each of the plurality of entities experiencing substantially the same behavior change, analyzing the substantially same behavior change of each of the plurality of entities to identify a portion of data related to processing of each of the plurality of entities, the processing occurring at a time prior to the detecting of the indicator of compromise; and
transmitting the indicator of compromise and the identified portion of data to a central computer for further analysis and modeling.

2. The method of claim 1 , wherein creating the entity group is performed responsive to receiving input from a user that specifies the plurality of entities belonging to the entity group.

3. The method of claim 1 , wherein creating the entity group is automatically performed and populated with the plurality of entities based on a set of one or more attributes common to those plurality of entities.

4. The method of claim 1 , wherein creating the entity group is automatically performed and populated with the plurality of entities based on those plurality of entities previously showing similar behavior.

5. The method of claim 1 , wherein the created behavior profile for each one of the plurality of entities of the entity group includes a set of one or more features that are used to distinguish behavior between the plurality of entities.

6. The method of claim 1 , wherein the created behavior profile for each one of the plurality of entities of the entity group includes a set of one or more features that are used to distinguish behavior of the created entity group as compared to behavior of a different entity group.

7. The method of claim 6 , wherein the set of features are extracted or derived from metadata and other items of interest including one or more of: network packets propagating to/from devices, log information, and flow based connection records.

8. The method of claim 1 ,
wherein the indicator of compromise includes a distance measure determined for each feature of a first behavior profile, combining the distance measure for each feature into a combined distance, and determining that the combined distance exceeds a predefined compromise threshold, and
wherein identifying the amount of data related to occurrences of the substantially same behavior change occurring during a previous time period is the amount of data that occurred after a trigger threshold, the trigger threshold being less than the predefined compromise threshold.

9. The method of claim 1 , wherein the multi-tier security framework includes (i) at least one network sensor engine configured to collect and store information associated with one or more of the plurality of entities, and (ii) a data analysis engine configured to perform analytics on the information associated with one or more of the plurality of entities.

10. The method of claim 1 , further comprising:
generating, by the multi-tier security framework, a user behavior risk score for each of the plurality of entities.

11. A non-transitory machine-readable storage medium that provides instructions that, if executed by a processor, will cause said processor to perform operations comprising:
creating an entity group that includes a plurality of entities, wherein each one of the plurality of entities represents one of a user, a machine, or a service;
creating a behavior profile for each one of the plurality of entities of the entity group;
monitoring behavior of each one of the plurality of entities of the entity group to detect behavior change;
detecting an indicator of compromise based on each of the plurality of entities experiencing substantially a same behavior change, the indicator of compromise identifying that a potential threat is directed toward a network including the plurality of entities;
responsive to detecting the indicator of compromise based on each of the plurality of entities experiencing substantially the same behavior change, analyzing the substantially same behavior change of each of the plurality of entities to identify a portion of data related to processing of each of the plurality of entities, the processing occurring at a time prior to the detecting of the indicator of compromise; and
transmitting the indicator of compromise and the identified portion of data to a central computer for further analysis and modeling.

12. The non-transitory machine-readable storage medium of claim 11 , wherein creating the entity group is performed responsive to receiving input from a user that specifies the plurality of entities belonging to the entity group.

13. The non-transitory machine-readable storage medium of claim 11 , wherein creating the entity group is automatically performed and populated with the plurality of entities based on a set of one or more attributes common to those plurality of entities.

14. The non-transitory machine-readable storage medium of claim 11 , wherein creating the entity group is automatically performed and populated with the plurality of entities based on those plurality of entities previously showing similar behavior.

15. The non-transitory machine-readable storage medium of claim 11 , wherein the created behavior profile for each one of the plurality of entities of the entity group includes a set of one or more features that are used to distinguish behavior between the plurality of entities.

16. The non-transitory machine-readable storage medium of claim 11 , wherein the created behavior profile for each one of the plurality of entities of the entity group includes a set of one or more features that are used to distinguish behavior of the created entity group as compared to behavior of a different entity group.

17. The non-transitory machine-readable storage medium of claim 16 , wherein the set of features are extracted or derived from metadata and other items of interest including one or more of: network packets propagating to/from devices, log information, and flow based connection records.

18. The non-transitory machine-readable storage medium of claim 11 ,
wherein detecting an indicator of compromise includes determining a distance measure determined for each feature of a first behavior profile, combining the distance measure for each feature into a combined distance, and determining that the combined distance exceeds a predefined compromise threshold, and
wherein identifying the amount of data related to occurrences of the substantially same behavior change occurring during a previous time period is the amount of data that occurred after a trigger threshold, the trigger threshold being less than the predefined compromise threshold.

19. An apparatus for collaborati

Assignees

• Niara Inc
• Hewlett Packard Entpr Dev Lp

Inventors

• Wang Jisheng

Classifications

• H04L63/1425 Primary

  Traffic logging, e.g. anomaly detection · CPC title

• H04W4/38

  for collecting sensor information · CPC title