EnSolver: Uncertainty-Aware Ensemble CAPTCHA Solvers with Theoretical Guarantees

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hoang, Duc C., Ousat, Behzad, Kharraz, Amin, Nguyen, Cuong V.
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909233115561984
author Hoang, Duc C.
Ousat, Behzad
Kharraz, Amin
Nguyen, Cuong V.
author_facet Hoang, Duc C.
Ousat, Behzad
Kharraz, Amin
Nguyen, Cuong V.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2307_15180
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EnSolver: Uncertainty-Aware Ensemble CAPTCHA Solvers with Theoretical Guarantees
Hoang, Duc C.
Ousat, Behzad
Kharraz, Amin
Nguyen, Cuong V.
Computer Vision and Pattern Recognition
Cryptography and Security
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.
title EnSolver: Uncertainty-Aware Ensemble CAPTCHA Solvers with Theoretical Guarantees
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2307.15180