破解 reCAPTCHAv2

Breaking reCAPTCHAv2

September 13, 2024

作者: Andreas Plesner, Tobias Vontobel, Roger Wattenhofer

cs.AI

摘要

我們的研究探討了利用先進機器學習方法解決 Google 的 reCAPTCHAv2 系統中的驗證碼的效能。我們通過利用先進的 YOLO 模型進行圖像分割和分類來評估自動系統解決驗證碼的效果。我們的主要結果是，我們可以解決100%的驗證碼，而先前的研究僅解決了68-71%。此外，我們的研究結果表明，在 reCAPTCHAv2 中，人類和機器人必須解決的挑戰數量沒有顯著差異。這意味著當前的人工智慧技術可以利用先進的基於圖像的驗證碼。我們還深入研究了 reCAPTCHAv2，發現證據表明 reCAPTCHAv2 在評估用戶是否為人類時，主要基於 cookie 和瀏覽器歷史數據。本文附帶代碼。

English

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.