# An Empirical Study & Evaluation of Modern CAPTCHAs

arXiv: https://arxiv.org/abs/2307.12108 · HTML: https://mlsanity.com/paper/2307.12108/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2023.

## Built on by (most cited first, 13 of 13)

- [Infrastructure for AI Agents](https://mlsanity.com/paper/2501.10114/) (2025)
- [MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks](https://mlsanity.com/paper/2506.05982/) (2025)
- [COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers](https://mlsanity.com/paper/2512.02318/) (2025)
- [When Incentives Backfire, Data Stops Being Human](https://mlsanity.com/paper/2502.07732/) (2025)
- [CAPTURE: A Benchmark and Evaluation for LVLMs in CAPTCHA Resolving](https://mlsanity.com/paper/2512.11323/) (2025)
- [CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training](https://mlsanity.com/paper/2603.23559/) (2026)
- [Personhood Credentials: Human-Centered Design Recommendation Balancing Security, Usability, and Trust](https://mlsanity.com/paper/2502.16375/) (2025)
- [Predictive Response Optimization: Using Reinforcement Learning to Fight Online Social Network Abuse](https://mlsanity.com/paper/2502.17693/) (2025)
- [VIPER Strike: Defeating Visual Reasoning CAPTCHAs via Structured Vision-Language Inference](https://mlsanity.com/paper/2601.06461/) (2026)
- [HLL: Can Agents Cross Humanity's Last Line of Verification?](https://mlsanity.com/paper/2606.02449/) (2026)
- [Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs](https://mlsanity.com/paper/2607.27951/) (2026)
- [CaptchaAgent: Verifiable Visual Reasoning for CAPTCHA Solving](https://mlsanity.com/paper/2610.12866/) (2026)
- [DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates](https://mlsanity.com/paper/2610.19830/) (2026)

## Abstract (arXiv)

For nearly two decades, CAPTCHAs have been widely used as a means of protection against bots. Throughout the years, as their use grew, techniques to defeat or bypass CAPTCHAs have continued to improve. Meanwhile, CAPTCHAs have also evolved in terms of sophistication and diversity, becoming increasingly difficult to solve for both bots (machines) and humans. Given this long-standing and still-ongoing arms race, it is critical to investigate how long it takes legitimate users to solve modern CAPTCHAs, and how they are perceived by those users. In this work, we explore CAPTCHAs in the wild by evaluating users' solving performance and perceptions of unmodified currently-deployed CAPTCHAs. We obtain this data through manual inspection of popular websites and user studies in which 1,400 participants collectively solved 14,000 CAPTCHAs. Results show significant differences between the most popular types of CAPTCHAs: surprisingly, solving time and user perception are not always correlated. We performed a comparative study to investigate the effect of experimental context -- specifically the difference between solving CAPTCHAs directly versus solving them as part of a more natural task, such as account creation. Whilst there were several potential confounding factors, our results show that experimental context could have an impact on this task, and must be taken into account in future CAPTCHA studies. Finally, we investigate CAPTCHA-induced user task abandonment by analyzing participants who start and do not complete the task.