Hacking Google reCAPTCHA v3 using Reinforcement Learning

2019/03/03 by Ismail Akrout, Amal Feriani, Akrout, Ismail +3 · 2 voices · 1 citation
Computer Science · #User Authentication and Security Systems #Innovative Human-Technology Interaction #Advanced Malware Detection Techniques

paper · pdf · doi:10.48550/arxiv.1903.01003

Abstract

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.

Cited by

• COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers

Discussions

• Hacking Google ReCAPTCHA v3 Using Reinforcement Learning (2019) [hn, 100 points, 24 comments]
• Hacking Google ReCAPTCHA v3 Using Reinforcement Learning [hn, 55 points, 43 comments]

Related

• Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
• RL-GPT: Integrating Reinforcement Learning and Code-as-policy
• AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement\n Learning
• Deep Reinforcement Learning Agents are not even close to Human Intelligence
• Distilling Reinforcement Learning Tricks for Video Games