Challenge-response authentication using generative artificial intelligence

Patent metadata

Field	Value
Publication number	US-2026010591-A1
Application number	US-202418762810-A
Country	US
Kind code	A1
Filing date	Jul 3, 2024
Priority date	Jul 3, 2024
Publication date	Jan 8, 2026
Grant date	—

Abstract

Computer-implemented methods for a challenge-response authentication system using generative artificial intelligence (AI). Aspects include generating a prompt for an object of a randomly selected output type. Aspects further include generating a solution object of the randomly selected output type based on the prompt using a generative AI engine. Aspects also include generating a candidate object of the randomly selected output type based on a modified prompt using the generative AI engine. Aspects further include presenting a challenge-response test comprising a question based on the prompt, the solution object, and the candidate object to a user device. Aspects also include performing a responsive action in response to receiving a response to the challenge-response test from the user device comprising an object selection.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
generating a prompt for an object of a randomly selected output type; generating a solution object of the randomly selected output type based on the prompt using a generative artificial intelligence (AI) engine; generating a candidate object of the randomly selected output type based on a modified prompt using the generative AI engine; presenting a challenge-response test comprising a question based on the prompt, the solution object, and the candidate object to a user device; and in response to receiving a response to the challenge-response test from the user device comprising an object selection, performing a responsive action.

2 . The computer-implemented method of claim 1 , wherein the generative AI engine is a text-to-image generative AI engine, a text-to-video generative AI engine, a text-to-audio generative AI engine, or a text-to-text generative AI engine.

3 . The computer-implemented method of claim 1 , wherein the responsive action comprises:
determining that the object selection of the response matches the solution object; and granting the user device access to a protected resource.

4 . The computer-implemented method of claim 1 , wherein the responsive action comprises:
determining that the object selection of the response does not match the solution object; and performing a security action comprising preventing access to a protected resource for the user device or presenting a second question, a second solution object, and a second candidate object to the user of the user device.

5 . The computer-implemented method of claim 1 , further comprising generating the modified prompt by removing an entity from the prompt.

6 . The computer-implemented method of claim 1 , further comprising:
generating, by a text-to-text generative AI engine, the question based on the prompt.

7 . The computer-implemented method of claim 1 , wherein the randomly selected output type is audio, video, text, or image.

8 . A system comprising:
a memory having computer readable instructions; and one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
generating a prompt for an object of a randomly selected output type;
generating a solution object of the randomly selected output type based on the prompt using a generative artificial intelligence (AI) engine;
generating a candidate object of the randomly selected output type based on a modified prompt using the generative AI engine;
presenting a challenge-response test comprising a question based on the prompt, the solution object, and the candidate object to a user device; and
in response to receiving a response to the challenge-response test from the user device comprising an object selection, performing a responsive action.

9 . The system of claim 8 , wherein the generative AI engine is a text-to-image generative AI engine, a text-to-video generative AI engine, a text-to-audio generative AI engine, or a text-to-text generative AI engine.

10 . The system of claim 8 , wherein the responsive action comprises:
determining that the object selection of the response matches the solution object; and granting the user device access to a protected resource.

11 . The system of claim 8 , wherein the responsive action comprises:
determining that the object selection of the response does not match the solution object; and performing a security action comprising preventing access to a protected resource for the user device or presenting a second question, a second solution object, and a second candidate object to the user of the user device.

12 . The system of claim 8 , wherein the operations further comprise generating the modified prompt by removing an entity from the prompt.

13 . The system of claim 8 , wherein the operations further comprise:
generating, by a text-to-text generative AI engine, the question based on the prompt.

14 . The system of claim 8 , wherein the randomly selected output type is audio, video, text, or image.

15 . A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:
generating a prompt for an object of a randomly selected output type; generating a solution object of the randomly selected output type based on the prompt using a generative artificial intelligence (AI) engine; generating a candidate object of the randomly selected output type based on a modified prompt using the generative AI engine; presenting a challenge-response test comprising a question based on the prompt, the solution object, and the candidate object to a user device; and in response to receiving a response to the challenge-response test from the user device comprising an object selection, performing a responsive action.

16 . The computer program product of claim 15 , wherein the generative AI engine is a text-to-image generative AI engine, a text-to-video generative AI engine, a text-to-audio generative AI engine, or a text-to-text generative AI engine.

17 . The computer program product of claim 15 , wherein the responsive action comprises:
determining that the object selection of the response matches the solution object; and granting the user device access to a protected resource.

18 . The computer program product of claim 15 , wherein the responsive action comprises:
determining that the object selection of the response matches the solution object; and performing a security action comprising preventing access to a protected resource for the user device or presenting a second question, a second solution object, and a second candidate object to the user of the user device.

19 . The computer program product of claim 15 , wherein the operations further comprise generating the modified prompt by removing an entity from the prompt.

20 . The computer program product of claim 15 , wherein the operations further comprise:
generating, by a text-to-text generative AI engine, the question based on the prompt.

Assignees

• Kyndryl Inc

Inventors

• Rodriguez Bravo Cesar Augusto
• Eckert Kim A
• Bode Chris

Classifications

• G06F2221/2133

  Verifying human interaction, e.g., Captcha · CPC title

• G06F21/31 Primary

  User authentication · CPC title