EnSolver: Uncertainty-Aware Ensemble CAPTCHA Solvers with Theoretical Guarantees
This addresses security vulnerabilities in CAPTCHA systems for website protection, but it is incremental as it builds on existing solvers with uncertainty detection.
The paper tackles the problem of CAPTCHA solvers performing poorly on out-of-distribution samples and being detectable by defense systems, proposing EnSolver, which uses deep ensemble uncertainty to detect and skip such samples, with experiments showing it performs well on mixed datasets.
The popularity of text-based CAPTCHA as a security mechanism to protect websites from automated bots has prompted researches in CAPTCHA solvers, with the aim of understanding its failure cases and subsequently making CAPTCHAs more secure. Recently proposed solvers, built on advances in deep learning, are able to crack even the very challenging CAPTCHAs with high accuracy. However, these solvers often perform poorly on out-of-distribution samples that contain visual features different from those in the training set. Furthermore, they lack the ability to detect and avoid such samples, making them susceptible to being locked out by defense systems after a certain number of failed attempts. In this paper, we propose EnSolver, a family of CAPTCHA solvers that use deep ensemble uncertainty to detect and skip out-of-distribution CAPTCHAs, making it harder to be detected. We prove novel theoretical bounds on the effectiveness of our solvers and demonstrate their use with state-of-the-art CAPTCHA solvers. Our experiments show that the proposed approaches perform well when cracking CAPTCHA datasets that contain both in-distribution and out-of-distribution samples.