Threat mitigation system and method

Patent metadata

Field	Value
Publication number	US-12549593-B2
Application number	US-202418584996-A
Country	US
Kind code	B2
Filing date	Feb 22, 2024
Priority date	Feb 23, 2023
Publication date	Feb 10, 2026
Grant date	Feb 10, 2026

Abstract

A computer-implemented method, computer program product and computing system for defining a formatting script for use with a Generative AI Model; receiving a notification of a security event, wherein the notification includes a computer-readable language portion that defines one or more specifics of the security event; and processing at least a portion of the computer-readable language portion of the notification using the Generative AI Model and the formatting script to summarize the computer-readable language portion and generate a summarized human-readable report.

First claim

What is claimed is:

1 . A computer-implemented method executed on a computing device comprising:
defining a formatting script for use with a Generative AI Model, wherein the formatting script is configured to one or more of:
clean and structure user queries for the Generative AI Model; and
format prompts for a specific Generative AI Model;
receiving a notification of a security event from at least one of a plurality of agents executed at least one of a plurality of security-relevant subsystems within a computing platform, wherein the notification includes a computer-readable language portion that defines one or more specifics of the security event; and processing at least a portion of the computer-readable language portion of the notification using the Generative AI Model and the formatting script to summarize the computer-readable language portion and generate a summarized human-readable report.

2 . The computer-implemented method of claim 1 wherein the computer-readable language portion includes a JSON portion.

3 . The computer-implemented method of claim 1 wherein the formatting script includes one or more discrete instructions for the Generative AI Model.

4 . The computer-implemented method of claim 1 further comprising:
presenting the summarized human-readable report to a user.

5 . The computer-implemented method of claim 1 further comprising:
prompting a user to provide feedback concerning the summarized human-readable report.

6 . The computer-implemented method of claim 1 further comprising:
receiving feedback concerning the summarized human-readable report from a user.

7 . The computer-implemented method of claim 6 further comprising:
utilizing the feedback to revise the formatting script.

8 . A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
defining a formatting script for use with a Generative AI Model, wherein the formatting script is configured to one or more of:
clean and structure user queries for the Generative AI Model; and
format prompts for a specific Generative AI Model;
receiving a notification of a security event from at least one of a plurality of agents executed at least one of a plurality of security-relevant subsystems within a computing platform, wherein the notification includes a computer-readable language portion that defines one or more specifics of the security event; and processing at least a portion of the computer-readable language portion of the notification using the Generative AI Model and the formatting script to summarize the computer-readable language portion and generate a summarized human-readable report.

9 . The computer program product of claim 8 wherein the computer-readable language portion includes a JSON portion.

10 . The computer program product of claim 8 wherein the formatting script includes one or more discrete instructions for the Generative AI Model.

11 . The computer program product of claim 8 further comprising:
presenting the summarized human-readable report to a user.

12 . The computer program product of claim 8 further comprising:
prompting a user to provide feedback concerning the summarized human-readable report.

13 . The computer program product of claim 8 further comprising:
receiving feedback concerning the summarized human-readable report from a user.

14 . The computer program product of claim 13 further comprising:
utilizing the feedback to revise the formatting script.

15 . A computing system including a processor and memory configured to perform operations comprising:
defining a formatting script for use with a Generative AI Model, wherein the formatting script is configured to one or more of:
clean and structure user queries for the Generative AI Model; and
format prompts for a specific Generative AI Model;
receiving a notification of a security event from at least one of a plurality of agents executed at least one of a plurality of security-relevant subsystems within a computing platform, wherein the notification includes a computer-readable language portion that defines one or more specifics of the security event; and processing at least a portion of the computer-readable language portion of the notification using the Generative AI Model and the formatting script to summarize the computer-readable language portion and generate a summarized human-readable report.

16 . The computing system of claim 15 wherein the computer-readable language portion includes a JSON portion.

17 . The computing system of claim 15 wherein the formatting script includes one or more discrete instructions for the Generative AI Model.

18 . The computing system of claim 15 further comprising:
presenting the summarized human-readable report to a user.

19 . The computing system of claim 15 further comprising:
prompting a user to provide feedback concerning the summarized human-readable report.

20 . The computing system of claim 15 further comprising:
receiving feedback concerning the summarized human-readable report from a user.

21 . The computing system of claim 20 further comprising:
utilizing the feedback to revise the formatting script.

Assignees

• Reliaquest Holdings Llc

Inventors

• Murphy Brian P
• Partlow Joe
• O'Connor Colin
• Pfeiffer Jason
• Murphy Brian Philip
• Echavarria Jonathan R

Classifications

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• G06F40/56

  Natural language generation · CPC title

• G06F21/566

  Dynamic detection, i.e. detection performed at run-time, e.g. emulation, suspicious activities · CPC title

• G06N3/0475 Primary

  Generative networks · CPC title

• G06F2221/034

  Test or assess a computer or a system · CPC title