mlsanityData to 7 Oct 2026

Breaking reCAPTCHAv2

arXiv 2409.08831 ↗First posted 13 Sep 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Our work examines the efficacy of employing advanced machine learning methods to solve captchas from Google's reCAPTCHAv2 system. We evaluate the effectiveness of automated systems in solving captchas by utilizing advanced YOLO models for image segmentation and classification. Our main result is that we can solve 100% of the captchas, while previous work only solved 68-71%. Furthermore, our findings suggest that there is no significant difference in the number of challenges humans and bots must solve to pass the captchas in reCAPTCHAv2. This implies that current AI technologies can exploit advanced image-based captchas. We also look under the hood of reCAPTCHAv2, and find evidence that reCAPTCHAv2 is heavily based on cookie and browser history data when evaluating whether a user is human or not. The code is provided alongside this paper.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 11 of its 36 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

11 of 36 references.

References · 11

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2021Transformers in Vision: A Surveycited by 1,009
  9. 2017Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Videocited by 30
  10. 2020Deep-CAPTCHA: a deep learning based CAPTCHA solver for vulnerability assessmentcited by 11
  11. 2021An Object Detection based Solver for Google's Image reCAPTCHA v2cited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 4.

12 papers.

  1. 2025Frontier AI's Impact on the Cybersecurity Landscapecited by 21
  2. 2025Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agentscited by 14
  3. 2024AI and the Future of Digital Public Squarescited by 6
  4. 2025COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solverscited by 4
  5. 2025LLM Agents Are the Antidote to Walled Gardenscited by 3
  6. 2025Aura-CAPTCHA: A Reinforcement Learning and GAN-Enhanced Multi-Modal CAPTCHA Systemcited by 3
  7. 2026Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defensecited by 2
  8. 2025The Impact of Scaling Training Data on Adversarial Robustnesscited by 1
  9. 2026HLL: Can Agents Cross Humanity's Last Line of Verification?cited by 1
  10. 2025Benchmarking of Different YOLO Models for CAPTCHAs Detection and Classificationcited by 0
  11. 2026Process Matters more than Output for Distinguishing Humans from Machinescited by 0
  12. 2026CAPTCHAs in the Agentic Era: Solvers That Learn from Every Encountercited by 0