Hacking Google reCAPTCHA v3 using Reinforcement Learning
This addresses security vulnerabilities in CAPTCHA systems, which are widely used for bot detection, but it is incremental as it builds on existing reinforcement learning techniques.
The paper tackled the problem of bypassing Google reCAPTCHA v3 by formulating it as a grid world and using reinforcement learning to control mouse movements and clicks, achieving success rates of 97.4% on a 100x100 grid and 96.7% on a 1000x1000 screen resolution.
We present a Reinforcement Learning (RL) methodology to bypass Google reCAPTCHA v3. We formulate the problem as a grid world where the agent learns how to move the mouse and click on the reCAPTCHA button to receive a high score. We study the performance of the agent when we vary the cell size of the grid world and show that the performance drops when the agent takes big steps toward the goal. Finally, we used a divide and conquer strategy to defeat the reCAPTCHA system for any grid resolution. Our proposed method achieves a success rate of 97.4% on a 100x100 grid and 96.7% on a 1000x1000 screen resolution.