MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (44) · 38039-38047
DOI: 10.1609/aaai.v40i44.41141 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zonglin Wu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
As automated attack techniques rapidly advance, CAPTCHAs remain a critical defense mechanism against malicious bots. However, existing CAPTCHA schemes encompass a diverse range of modalities—from static distorted text and obfuscated images to interactive clicks, sliding puzzles, and logic-based questions—yet the community still lacks a unified, large-scale, multimodal benchmark to rigorously evaluate their security robustness. To address this gap, we introduce MCA-Bench, a comprehensive and reproducible benchmarking suite that integrates heterogeneous CAPTCHA types into a single evaluation protocol. Leveraging a shared vision–language model backbone, we fine-tune specialized cracking agents for each CAPTCHA category, enabling consistent, cross-modal assessments. Extensive experiments reveal that MCA-Bench effectively maps the vulnerability spectrum of modern CAPTCHA designs under varied attack settings, and—crucially—offers the first quantitative analysis of how challenge complexity, interaction depth, and model solvability interrelate. Based on these findings, we propose three actionable design principles and identify key open challenges, laying the groundwork for systematic CAPTCHA hardening, fair benchmarking, and broader community collaboration.
Zitieren
APA
Wu, Z., Xue, Y., Feng, Y., Wang, X., & Song, Y. (2026). MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, 40(44), 38039-38047. https://doi.org/10.1609/aaai.v40i44.41141
Vancouver
Wu Z, Xue Y, Feng Y, Wang X, Song Y. MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(44):38039-38047. doi:10.1609/aaai.v40i44.41141
BibTeX
@article{Wu2026,
author = {Wu, Zonglin and Xue, Yule and Feng, Yaoyao and Wang, Xiaolong and Song, Yiren},
title = {MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {44},
pages = {38039--38047},
doi = {10.1609/aaai.v40i44.41141}
}
EUVIMED