Granted Patent B1

US 12,659,333 · App. 18/635,901 · Granted Jun 16, 2026

Inventors: Galen Emery (San Diego, CA); Dan Daggett, II (San Diego, CA); Drew A. Khorasani (Escondido, CA); Gregory M. Sloan (Orange, CA); Craig J. Beyer, Jr. (New York, NY); Yijou Chen (Cupertino, CA)

Assignee: Fortinet, Inc.

H04L63/1425G06F9/455G06F9/545G06F16/9024G06F16/9038G06F16/9535G06F16/9537G06F21/57H04L43/045H04L43/06H04L63/10H04L67/306H04L67/535G06F16/2456

Abstract

Claims (40)

1 . A method comprising:

receiving, from a customer, data to be used to generate a capture-the-flag competition for an anomaly detection framework;

identifying, by a processor, one or more flags in the data, the one or more flags representing anomalies in the data;

providing a user interface for the capture-the-flag competition comprising challenges to identify the one or more flags in the data;

receiving, from one or more participants of the capture-the-flag competition, solutions to the challenges via the user interface;

performing one or more calculations to generate corresponding scores to the solutions received from the one or more participants;

generating a leaderboard using the corresponding scores for the one or more participants;

aggregating scores from other customers competing in other capture-the-flag competitions; and

generating another leaderboard comparing the corresponding scores for the one or more participants to the scores of the other customers.

2 . The method of claim 1 , further comprising:

receiving subsequent data from the customer;

identifying one or more subsequent flags in the subsequent data; and

updating the user interface to include challenges to identify the one or more subsequent flags in the subsequent data.

3 . The method of claim 1 , wherein the processor executes a generative artificial intelligence (AI) model to generate the capture-the-flag competition.

4 . The method of claim 3 , wherein the generative AI model generates the capture-the-flag competition while bypassing user interaction.

5 . The method of claim 1 , further comprising:

receiving heuristic data associated with the capture-the-flag competition; and

modifying at least one of the one or more flags or the challenges based on the received heuristic data.

6 . The method of claim 1 , wherein the solutions to the challenges utilize an application programming interface of the anomaly detection framework.

7 . The method of claim 1 , wherein the solutions to the challenges utilize a query language of the anomaly detection framework.

8 . A non-transitory computer readable storage medium storing instructions which, when executed, cause a processor to:

receive, from a customer, data from a customer to be used to generate a capture-the-flag competition for an anomaly detection framework;

identify one or more flags in the data, the one or more flags representing anomalies in the data; and

provide a user interface for the capture-the-flag competition comprising challenges to identify the one or more flags in the data;

receive heuristic data associated with the capture-the-flag competition;

modify at least one of the one or more flags or the challenges based on the received heuristic data;

perform one or more calculations to generate corresponding scores to the solutions received from the one or more participants; and

generate a leaderboard using the corresponding scores for the one or more participants.

9 . The non-transitory computer readable storage medium of claim 8 ,

wherein the processor is further to:

receive subsequent data from the customer;

identify one or more subsequent flags in the subsequent data; and

update the user interface to include challenges to identify the one or more subsequent flags in the subsequent data.

10 . The non-transitory computer readable storage medium of claim 8 , wherein the processor executes a generative artificial intelligence (AI) model to generate the capture-the-flag competition.

11 . The non-transitory computer readable storage medium of claim 10 , wherein the generative AI model generates the capture-the-flag competition while bypassing user interaction.

12 . The non-transitory computer readable storage medium of claim 10 , wherein the generative AI model is configured to generate a polygraph.

13 . The non-transitory computer readable storage medium of claim 8 , wherein the processor is further to:

receive, from one or more participants of the capture-the-flag competition, solutions to the challenges via the user interface.

14 . The non-transitory computer readable storage medium of claim 8 , wherein the solutions to the challenges utilize an application programming interface of the anomaly detection framework.

15 . The non-transitory computer readable storage medium of claim 8 , wherein the solutions to the challenges utilize a query language of the anomaly detection framework.

Assignments (1)

Continuity (7)

References Cited (400)