IP Library › Granted Patent US 11,928,631
Granted Patent B2
US 11,928,631 · App. 17/188,931 · Granted Mar 12, 2024

Threat detection with business impact scoring

Inventors: Russell Humphries (Surrey, GB); Andrew J. Thomas (Oxfordshire, GB)
Assignee: Sophos Limited
G06Q10/0635G06F9/542G06F11/079G06F16/955G06F17/18G06F18/214G06F18/2178G06F18/23213G06F18/24143G06F21/554G06F21/56G06F21/562G06F21/565G06N5/01G06N5/022G06N5/04G06N5/046G06N7/00G06N20/00G06N20/20G06Q10/06395G06V20/52H04L63/0227H04L63/0263H04L63/1408H04L63/1416H04L63/1425H04L63/1433H04L63/1441H04L63/20G06Q30/0185G06Q30/0283
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,928,631
App. No.
17/188,931
Filed
Mar 1, 2021
Granted
Mar 12, 2024
Kind
B2
Art Unit
3689
USPC
705/317
Abstract

A computer model is created for automatically evaluating the business value of computing objects such as files and databases on an endpoint. This can be used to assess the potential business impact of a security compromise to an endpoint, or a process executing on an endpoint, in order to prioritize potential threats within an enterprise for human review and intervention.

Claims (36)

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:

providing a training set of files including a first plurality of files each having a file location, an access control list, and known business value;

training a machine learning model to automatically estimate a business value of a sample file based on the training set of files;

analyzing a second plurality of files within an enterprise network for a threat level using a threat model based on one or more of behavioral tags, executable file paths, and Uniform Resource Locators;

identifying one or more intermediate threat samples within the second plurality of files that are not within a predetermined confidence level of safe or malicious according to the threat model;

determining an estimated business value for each of the one or more intermediate threat samples using the machine learning model;

ranking the one or more intermediate threat samples for presentation within a user interface based on a combination of a likelihood of maliciousness determined according to the threat model and the estimated business value determined according to the machine learning model; and

presenting the one or more intermediate threat samples to a user in the user interface for human evaluation.

2. The computer program product of claim 1 wherein the business value is further based on file content.

3. The computer program product of claim 1 wherein the business value is further based on an encryption status.

4. The computer program product of claim 1 wherein the business value is further based on a file type.

5. The computer program product of claim 1 wherein the business value is further based on a file usage history.

6. The computer program product of claim 1 wherein the business value is further based on a file creation date.

7. A method comprising:

providing a valuation model for automatically estimating a business value of a file, wherein providing the valuation model includes creating a model to estimate the business value based on a training set of files each having a known business value, wherein the business value is based on at least one of a file location and an access control list;

analyzing a plurality of files within an enterprise network for a threat level using an integrative model based on one or more of behavioral tags, executable file paths, and Uniform Resource Locators;

identifying one or more intermediate threats associated with the plurality of files that are not within a predetermined confidence level of safe or malicious according to the integrative model;

determining an estimated business value for each of the one or more intermediate threats using the valuation model;

ranking the one or more intermediate threats for presentation within a user interface based on a combination of a likelihood of maliciousness determined according to the integrative model and the estimated business value determined according to the valuation model; and

presenting the one or more intermediate threats to a user in the user interface for human evaluation.

8. The method of claim 7 wherein the valuation model includes a machine learning model trained to estimate the business value using the training set of files and the known business value.

9. The method of claim 7 wherein the integrative model is based on a combination of a first model configured to identify malicious code based on behavioral tags, a second model configured to identify malicious code based on an executable file path, and a third model configured to identify malicious code based on a Uniform Resource Locator within a threat sample.

10. The method of claim 7 wherein the business value is further based on one or more of file content, a file type, a file creation date, and a file modification date.

11. The method of claim 7 wherein the business value is further based on an encryption status.

12. The method of claim 7 wherein the business value is further based on a file usage history.

13. The method of claim 7 further comprising receiving a user-initiated remedial action for one of the intermediate threats in the user interface.

14. The method of claim 7 further comprising receiving a user risk assessment for one of the intermediate threats in the user interface.

15. The method of claim 7 further comprising remediating a risk to a high business value computing object in response to a user input in the user interface.

16. The method of claim 7 wherein the integrative model evaluates a potential threat by computer objects based on one or more of file behavior, file signature, file path, or Uniform Resource Locator.

17. The method of claim 7 wherein the integrative model includes one or more machine learning models trained to recognize potentially malicious code based on a training set of known safe and known unsafe threat samples.

18. The method of claim 7 wherein identifying the one or more intermediate threats includes analyzing one or more computing objects within the enterprise network.

19. The method of claim 18 wherein the one or more computing objects include at least one of a registry of system settings or a secure kernel cache of process information.

20. A system comprising:

a memory storing an integrative model and a valuation model, the integrative model configured to provide a quantitate assessment of threat for a threat sample based on one or more of behavioral tags, executable file paths, and Uniform Resource Locators and the valuation model configured to automatically estimate a business value of one or more files associated with the threat sample based on at least a file location and an access control list;

a threat management facility configured to apply the integrative model to new threat samples and to identify intermediate threats that are not within a predetermined likelihood of being safe or unsafe; and

a web server configured to display a list of the intermediate threats in a user interface for human evaluation, wherein the intermediate threats in the list of the intermediate threats are ranked according to a combination of a first score from the integrative model and a second score from the valuation model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 8, 2021
From: HUMPHRIES, RUSSELL; THOMAS, ANDREW J.
To: SOPHOS LIMITED
Reel/Frame 055520/0704 →
Continuity (3)
Continuation 16129183 · Sep 12, 2018
Provisional Application 62726174 · Aug 31, 2018
Related Publication 20210211441A1 · Jul 8, 2021