Centralized event detection

Patent metadata

Field	Value
Publication number	US-11995205-B2
Application number	US-202318096882-A
Country	US
Kind code	B2
Filing date	Jan 13, 2023
Priority date	Apr 13, 2018
Publication date	May 28, 2024
Grant date	May 28, 2024

Abstract

A threat management facility stores a number of entity models that characterize reportable events from one or more entities. A stream of events from compute instances within an enterprise network can then be analyzed using these entity models to detect behavior that is inconsistent or anomalous for one or more of the entities that are currently active within the enterprise network.

First claim

What is claimed is:

1. A computer program product comprising computer executable code embodied in a non-transitory computer readable medium that, when executing on one or more computing devices, performs the steps of:
storing a plurality of entity models for a plurality of different types of entities at a threat management facility for an enterprise network, the plurality of different types of entities forming a stack of assets for a compute instance, and each entity model of the plurality of entity models characterizing a baseline of expected events in an event vector space based on events from a corresponding entity in the stack of assets for the compute instance over an historical window;
instrumenting the compute instance to report event vectors in the event vector space based on one or more events from one or more sensors associated with entities in the stack of assets for the compute instance;
receiving an event stream at the threat management facility, the event stream including a plurality of the event vectors from the compute instance;
calculating a risk score for the compute instance based on a distance in the event vector space between at least one of the plurality of the event vectors and two or more of the entity models for the different types of entities in the stack of assets for the compute instance, wherein the two or more of the entity models include at least two of a hardware entity model, a software entity model, and a user for the compute instance; and
selecting a remedial action for the compute instance when the risk score exceeds a threshold.

2. The computer program product of claim 1 wherein at least one of the historical window and the threshold is algorithmically determined.

3. The computer program product of claim 1 wherein the threat management facility stores a plurality of entity models for a plurality of entities within the enterprise network.

4. The computer program product of claim 1 wherein the event stream includes event vectors from a plurality of compute instances associated with the enterprise network.

5. The computer program product of claim 1 wherein the event stream includes event vectors from two or more different entities in the stack of assets for the compute instance.

6. The computer program product of claim 1 further comprising code that performs the steps of monitoring the event stream and creating one or more of the plurality of entity models based on a baseline of event vectors for the corresponding entity in the event stream over an interval.

7. The computer program product of claim 6 further comprising code that performs the step of refining the one or more of the plurality of entity models based on additional event vectors in the event stream received after the one or more of the plurality of entity models is created.

8. The computer program product of claim 6 wherein instrumenting the compute instance includes configuring the compute instance to normalize at least one of the events from at least one of the one or more sensors.

9. The computer program product of claim 6 wherein instrumenting the compute instance includes configuring the compute instance to tokenize at least one of the events from at least one of the one or more sensors.

10. The computer program product of claim 6 wherein instrumenting the compute instance includes configuring the compute instance to encrypt at least one of the events from at least one of the one or more sensors.

11. The computer program product of claim 6 wherein instrumenting the compute instance includes prioritizing at least one of the events from at least one of the one or more sensors.

12. The computer program product of claim 1 wherein the distance is at least one of a Mahalanobis distance, a Euclidean distance, and a Minkowski distance.

13. The computer program product of claim 1 wherein the distance is evaluated using a k-nearest neighbor algorithm.

14. The computer program product of claim 1 , wherein the plurality of different types of entities forming the stack of assets includes at least one of an identity and access management system, a domain controller, and an application.

15. A method comprising:
storing a plurality of entity models for an enterprise network, the plurality of entity models forming a stack of assets for a compute instance, the stack of assets including at least one software entity model associated with the compute instance and at least one user associated with the compute instance;
instrumenting the compute instance to detect one or more events from each of a plurality of entities forming the stack of assets for the compute instance, the compute instance further instrumented to report a number of event vectors including the one or more events;
receiving an event stream of the number of event vectors from the compute instance;
calculating a risk score for the compute instance based on a multi-dimensional vector distance in an event vector space between one or more of the number of event vectors in the event stream and the entity models for each of the plurality of entities forming the stack of assets for the compute instance; and
selecting a remedial action for the compute instance based on the number of event vectors when the risk score exceeds a threshold.

16. The method of claim 15 wherein the threshold is algorithmically determined.

17. The method of claim 15 wherein the event stream includes event vectors from a plurality of compute instances associated with the enterprise network.

18. The method of claim 15 wherein at least one of the plurality of entities includes at least one of a domain controller, a physical device, a user, an operating system, and an application.

19. The method of claim 15 wherein calculating the risk score includes calculating the vector distance in the event vector space between one of the number of event vectors and two or more of the plurality of entity models.

20. The method of claim 15 wherein calculating the risk score includes evaluating the vector distance in the event vector space using a k-nearest neighbor algorithm.

21. A system comprising:
a compute instance associated with two or more entities in an enterprise network, the compute instance configured to detect one or more events associated with the compute instance and report an event vector including the one or more events to a remote resource; and
a threat management facility, the threat management facility including a memory storing a plurality of entity models including at least one model non-exclusively characterizing expected events in an event vector space for each one of a plurality of entities forming a stack of assets for the compute instance, the stack of assets including at least one hardware entity model and at least one software entity model associated with the compute instance, and the threat management facility configured to receive an event stream including the event vector, to calculate a risk score for the compute instance based on a multi-dimensional vector distance in the event vector space between the event vector and one of the plurality of entity models for each of the entities in the stack of assets for the compute instance, and to select a remedial action for the compute instance based on the event vector when the risk score exceeds a threshold.

Assignees

• Sophos Ltd

Inventors

• Levy Joseph H
• Thomas Andrew J
• Schiappa Daniel Salvatore
• Ray Kenneth D

Classifications

• G06F16/122

  using management policies (point-in-time backing up or restoration of persistent data G06F11/1446; file migration policies for HSM systems G06F16/185) · CPC title

• G06F21/6218 Primary

  to a system of files or objects, e.g. local or distributed file system or database · CPC title

• G06F16/137

  Hash-based (content-based indexing of textual data G06F16/31) · CPC title

• G06F16/285

  Clustering or classification · CPC title

• G06F16/93

  Document management systems · CPC title