IP Library Granted Patent US 12,511,368
Granted Patent B2
US 12,511,368 · App. 18/406,286 · Granted Dec 30, 2025

User-friendly and self-managed challenge-response authentication

Inventors: Cesar Augusto Rodriguez Bravo (Alajuela, CR); John Richard Feezell (Pikeville, TN); Kim A. Eckert (Austin, TX); David Alonso Campos Batista (Aurora, CR)
Assignee: Kyndryl, Inc.
G06F21/36G06T11/60G06F2221/2133
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 12,511,368
App. No.
18/406,286
Granted
Dec 30, 2025
Kind
B2
Abstract

Computer-implemented methods for a user-friendly and self-managed CAPTCHA system. Aspects include storing a copy of an image selected from a set of images as a source image. Aspects further include generating a reference image by applying an image obfuscation technique to the image and a challenge image by applying a different image obfuscation technique to the image. Aspects include dividing the challenge image into partitions and placing the partitions randomly on a virtual canvas. Aspects include displaying the reference image and the virtual canvas on a user device requesting to access a protected resource. Aspects include receiving a solution image comprising the partitions of the challenge image arranged by a user from the user device. Aspects also include generating a similarity score by comparing the source image and the solution image. Aspects further include determining that the similarity score is below a threshold value and performing a security action.

Claims (57)

1 . A computer-implemented method comprising:

storing a copy of an image selected from a set of images as a source image;

generating a reference image by applying an image obfuscation technique to the image and a challenge image by applying a different image obfuscation technique to the image;

dividing the challenge image into a random number of partitions and placing the partitions randomly on a virtual canvas;

displaying both the reference image and the virtual canvas with the partitions of the challenge image on a user device requesting to access a protected resource, such that both the reference image and the challenge image are concurrently visible on the user device to a user, wherein both the reference image and the challenge image are concurrently displayed to be different from the image;

receiving a solution image comprising the partitions of the challenge image arranged by the user from the user device;

generating a similarity score by comparing the source image and the solution image;

determining that the similarity score is below a threshold value; and

performing a security action.

2 . The computer-implemented method of claim 1 , wherein the image obfuscation technique comprises reshaping the image, or cropping the image to carve out one or more portions.

3 . The computer-implemented method of claim 1 , wherein the virtual canvas is larger than the challenge image.

4 . The computer-implemented method of claim 1 , wherein the security action comprises preventing access to the protected resource for the user device or presenting a second reference image and a second challenge image to the user of the user device.

5 . The computer-implemented method of claim 1 , further comprising:

receiving an indication to select the image from a sub-set of images;

selecting the image from the sub-set of images; and

updating metadata associated with the image to increase a counter indicating a number of times the image has been displayed.

6 . The computer-implemented method of claim 1 , wherein the set of images comprises images associated with an identified metadata.

7 . The computer-implemented method of claim 1 , further comprising:

applying an overlay image obfuscation technique on the partitions of the challenge image in the virtual canvas.

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:

storing a copy of an image selected from a set of images as a source image;

generating a reference image by applying an image obfuscation technique to the image and a challenge image by applying a different image obfuscation technique to the image;

dividing the challenge image into a random number of partitions and placing the partitions randomly on a virtual canvas;

displaying both the reference image and the virtual canvas with the partitions of the challenge image on a user device requesting to access a protected resource, such that both the reference image and the challenge image are concurrently visible on the user device to a user, wherein both the reference image and the challenge image are concurrently displayed to be different from the image;

receiving a solution image comprising the partitions of the challenge image arranged by the user from the user device;

generating a similarity score by comparing the source image and the solution image;

determining that the similarity score is below a threshold value; and

performing a security action.

9 . The system of claim 8 , wherein the image obfuscation technique comprises reshaping the image, cropping the image, applying 3D rotation and effects on the image, or applying an image filter to the image.

10 . The system of claim 8 , wherein the virtual canvas is larger than the challenge image.

11 . The system of claim 8 , wherein the security action comprises preventing access to the protected resource for the user device or presenting a second reference image and a second challenge image to the user of the user device.

12 . The system of claim 8 , wherein the operations further comprise:

receiving an indication to select the image from a sub-set of images;

selecting the image from the sub-set of images; and

updating metadata associated with the image to increase a counter indicating a number of times the image has been displayed.

13 . The system of claim 8 , wherein the set of images comprises images associated with an identified metadata.

14 . The system of claim 8 , wherein the operations further comprise:

applying an overlay image obfuscation technique on the partitions of the challenge image in the virtual canvas.

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:

storing a copy of an image selected from a set of images as a source image;

generating a reference image by applying an image obfuscation technique to the image and a challenge image by applying a different image obfuscation technique to the image;

dividing the challenge image into a random number of partitions and placing the partitions randomly on a virtual canvas;

displaying both the reference image and the virtual canvas with the partitions of the challenge image on a user device requesting to access a protected resource, such that both the reference image and the challenge image are concurrently visible on the user device to a user, wherein both the reference image and the challenge image are concurrently displayed to be different from the image;

receiving a solution image comprising the partitions of the challenge image arranged by the user from the user device;

generating a similarity score by comparing the source image and the solution image;

determining that the similarity score is below a threshold value; and

performing a security action.

16 . The computer program product of claim 15 , wherein the image obfuscation technique comprises reshaping the image, cropping the image, applying 3D rotation and effects on the image, or applying an image filter to the image.

17 . The computer program product of claim 15 , wherein the virtual canvas is larger than the challenge image.

18 . The computer program product of claim 15 , wherein the security action comprises preventing access to the protected resource for the user device or presenting a second reference image and a second challenge image to the user of the user device.

19 . The computer program product of claim 15 , wherein the operations further comprise:

receiving an indication to select the image from a sub-set of images;

selecting the image from the sub-set of images; and

updating metadata associated with the image to increase a counter indicating a number of times the image has been displayed.

20 . The computer program product of claim 15 , wherein the set of images comprises images associated with an identified metadata.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 8, 2024
From: RODRIGUEZ BRAVO, CESAR AUGUSTO; FEEZELL, JOHN RICHARD; ECKERT, KIM A.; CAMPOS BATISTA, DAVID ALONSO
To: KYNDRYL, INC.
Reel/Frame 066045/0948 →
Continuity (1)
Related Publication 20250225224A1 · Jul 10, 2025
References Cited (30)
US 8209743B1 · Frank · 2012 [cited by examiner]
US 8904493B1 · Dibble · 2014 [cited by examiner]
US 9192861B2 · Gross · 2015 [cited by applicant]
US 9600678B1 · Alamuri · 2017 [cited by examiner]
US 10007776B1 · Bailey et al. · 2018 [cited by applicant]
US 10915610B2 · Jadhav et al. · 2021 [cited by applicant]
US 20080209223A1 · Nandy et al. · 2008 [cited by applicant]
US 20090313694A1 · Mates · 2009 [cited by examiner]
US 20100262662A1 · Wang · 2010 [cited by examiner]
US 20120195517A1 · Mittur · 2012 [cited by examiner]
US 20120323700A1 · Aleksandrovich · 2012 [cited by examiner]
US 20140059663A1 · Rajshekar · 2014 [cited by examiner]
US 20170337373A1 · Conti · 2017 [cited by examiner]
US 20180189471A1 · Paluri · 2018 [cited by examiner]
US 20190303555A1 · Agarwal · 2019 [cited by examiner]
US 20200134159A1 · Ford · 2020 [cited by examiner]
US 20210387094A1 · Young et al. · 2021 [cited by applicant]
CN 104618350B · 2018 [cited by applicant]
Anonymous, “Capy Puzzle CAPTCHA solving service,” URL: https://2captcha.com/p/capy_puzzle; Retrieved: Oct. 10, 2023; 5 pages. [cited by applicant]
Anonymous, “Capy Puzzle CAPTCHA,” URL: https://www.capy.me/products/puzzle_captcha/; Retrieved: Oct. 10, 2023; 1 page. [cited by applicant]
Anonymous, “Geetest-Slice-Captcha-Solver,” URL: https://github.com/peduajo/geetest-slice-captcha-solver; Retrieved: Oct. 10, 2023; 2 pages. [cited by applicant]
Anonymous, “How to bypass slider captcha to solve puzzle using selenium?(Python),” URL: https://stackoverflow.com/questions/72825192/how-to-bypass-slider-captcha-to-solve-puzzle-using-seleniumpython; Retrieved: Oct. 10,… [cited by applicant]
Anonymous, “Random Crop,” URL: https://hasty.ai/docs/mp-wiki/augmentations/random-crop; Retrieved: Oct. 10, 2023; 3 pages. [cited by applicant]
D'souza et al., “Avatar CAPTCHA: Telling Computers and Humans Apart via Face Classification,” IEEE International Conference on Electro/Information Technology, May 6-8, 2012, 6 pages. [cited by applicant]
D'souza, “Avatar Captcha : Telling Computers and Humans apart via Face Classification and Mouse Dynamics,” Electronic Theses and Dissertations, Paper 1715, 2014, 116 pages. [cited by applicant]
Dzieza, “Why CAPTCHAs have gotten so difficult,” The Verge, Feb. 1, 2019, 7 pages. [cited by applicant]
Korayem et al., “Solving Avatar Captchas Automatically,” Advanced Machine Learning Technologies and Applications: First International Conference, Dec. 2012, 9 pages. [cited by applicant]
Nelson, “Why and How to Implement Random Crop Data Augmentation,” Roboflow, Feb. 21, 2020, 7 pages. [cited by applicant]
Takahaski et al., “Data Augmentation using Random Image Cropping and Patching for Deep CNNs,” Journal of Latex Class Files, vol. 14, No. 8, Aug. 2015, 16 pages. [cited by applicant]
Wickramasingha et al., “RotateCAPTCHA—A Novel Interactive CAPTCHA Design Targeting Mobile Devices,” IEEE 10th International Conference on Industrial and Information Systems, Dec. 18-20, 2015, pp. 49-54. [cited by applicant]