IP Library Granted Patent US 12,470,556
Granted Patent B2
US 12,470,556 · App. 18/213,010 · Granted Nov 11, 2025

Generating captchas using generative imaging models

Inventors: Shawn Cantin Callegari (Bellevue, WA); Shane Michael Chism (Bellevue, WA); Chipalo N. Street (Seattle, WA); Nicholas Becker (Boulder, CO)
Assignee: Microsoft Technology Licensing, LLC
H04L63/10G06F2221/2133
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 12,470,556
App. No.
18/213,010
Granted
Nov 11, 2025
Kind
B2
Abstract

Methods and systems for generating completely automated public Turing test (CAPTCHA) images are provided. In some examples, a method includes generating a plurality of images using a generative imaging model, providing the plurality of images to a user with a description that corresponds to one of a similarity or difference between the plurality of images, receiving a selection of an image of the plurality of images, determining if the selection is correct based on the provided description, and outputting an indication of whether the selection is correct.

Claims (50)

1 . A method for generating captcha images, the method comprising:

generating a plurality of images using a generative imaging model, the generating comprising providing a plurality of prompts to the generative imaging model, each prompt of the plurality of prompts corresponding to a respective image of the plurality of images;

providing the plurality of images to a user with a description corresponding to one of a similarity or difference between the plurality of images;

receiving a selection of an image of the plurality of images;

determining if the selection is correct based on the provided description and the plurality of prompts provided to the generative imaging model;

outputting an indication of whether the selection is correct; and

if the description is correct, based on the indication, granting a user access to a computer system protected by the generated images or, if the description is incorrect, based on the indication, rejecting access to the computer system.

2 . The method of claim 1 , wherein each of the plurality of images are generated based on a plurality of categories of variables.

3 . The method of claim 2 , wherein the plurality of categories of variables comprise a subject, a verb, a setting, and a style.

4 . The method of claim 2 , wherein the similarity or difference is associated with a category of the plurality of categories of variables.

5 . The method of claim 1 , wherein the providing a plurality of images comprises displaying the plurality of images on a display screen of a computing device.

6 . The method of claim 1 , wherein the plurality of images is a first plurality of images, wherein the indication indicates that the selection is not correct, and wherein the method further comprises generating a second plurality of images using the generative imaging model.

7 . The method of claim 1 , wherein the indication indicates that the description is not correct, and wherein the method further comprises:

receiving a signal corresponding to the user terminating providing descriptions; and

providing the prompt based on which the one or more images were generated.

8 . A method for generating captcha images, the method comprising:

generating one or more images using a generative imaging model, wherein each of the one or more images are generated based on a respective prompt;

providing the one or more images to a user;

receiving a description of the one or more images;

comparing the description of the one or more images to the respective prompts of the images, wherein the comparing comprises:

generating an input embedding based on the received description;

generating a prompt embedding based on the prompts used to generate the one or more images;

determining a semantic distance between the input embedding and the prompt embedding within a vector space; and

comparing the semantic distance to a similarity threshold, thereby determining if the description is correct;

outputting an indication of whether the description is correct, based on the comparison; and

if the description is correct, based on the indication, granting a user access to a computer system protected by the generated images or, if the description is incorrect, based on the indication, not granting access to the computer system.

9 . The method of claim 8 , wherein the description comprises natural language.

10 . The method of claim 8 , wherein each of the plurality of images are generated based on a plurality of categories of variables.

11 . The method of claim 10 , wherein the plurality of categories of variables comprise a subject, a verb, a setting, and a style.

12 . The method of claim 8 , wherein the one or more images are a plurality of images, and wherein the description comprises a description of one of a similarity or difference between the plurality of images.

13 . The method of claim 8 , wherein the providing a plurality of images comprises displaying the plurality of images on a display screen of a computing device.

14 . The method of claim 8 , wherein the indication indicates that the description is not correct, and wherein the method further comprises:

receiving a signal corresponding to the user terminating providing descriptions; and

providing the prompt based on which the one or more images were generated.

15 . A method for generating captcha images, the method comprising:

generating a plurality of images using a generative imaging model, wherein each image of the plurality of images is generated based on a respective prompt;

providing the plurality of images to a user;

receiving a description of similarities or differences between the plurality of images;

comparing the description to similarities or differences between the prompts based on which the plurality of images were generated;

outputting an indication of whether the description is correct, based on the comparison; and

if the description is correct, based on the indication, granting a user access to a computer system protected by the generated images or, if the description is incorrect, based on the indication, rejecting access to the computer system.

16 . The method of claim 15 , wherein the description comprises natural language.

17 . The method of claim 15 , wherein each of the plurality of images are generated based on a plurality of categories of variables.

18 . The method of claim 17 , wherein the plurality of categories of variables comprise a subject, a verb, a setting, and a style.

19 . The method of claim 18 , wherein the similarities or differences between the prompts are based on similarities or differences between the plurality of categories of variables.

20 . The method of claim 15 , wherein the comparing comprises:

generating an input embedding based on the received description of similarities or differences;

generating a prompt embedding based on the similarities or difference between the prompts;

determining a distance between the input embedding and the prompt embedding within a vector space; and

comparing the distance to a similarity threshold, thereby determining if the description is correct.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 23, 2023
From: CALLEGARI, SHAWN CANTIN; CHISM, SHANE MICHAEL; STREET, CHIPALO N.; BECKER, NICHOLAS
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 064676/0545 →
Continuity (2)
Provisional Application 63453902 · Mar 22, 2023
Related Publication 20240320310A1 · Sep 26, 2024
References Cited (15)
US 8904493B1 · Dibble · 2014 [cited by examiner]
US 10496809B1 · Pham · 2019 [cited by applicant]
US 10614207B1 · Truong · 2020 [cited by applicant]
US 10839066B1 · Pham · 2020 [cited by examiner]
US 11461782B1 · Zettler, Jr. · 2022 [cited by examiner]
US 20100161927A1 · Sprouse · 2010 [cited by examiner]
US 20140059659A1 · Parekh · 2014 [cited by examiner]
US 20140196133A1 · Shuster · 2014 [cited by examiner]
US 20180373860A1 · Li · 2018 [cited by examiner]
US 20210141876A1 · Veshchikov · 2021 [cited by examiner]
US 20210216613A1 · Kumar · 2021 [cited by examiner]
US 20210387094A1 · Young · 2021 [cited by examiner]
US 20220350909A1 · Kawakita · 2022 [cited by examiner]
Cheng, et al., “Image-based CAPTCHAs based on neural style transfer”, IET Information Security, vol. 13, Issue 6, Nov. 1, 2019, pp. 519-529. [cited by applicant]
International Search Report and Written Opinion received for PCT Application No. PCT/US2024/18196, Jun. 19, 2024, 13 pages. [cited by applicant]