Abstract:We present Aura-CAPTCHA, a multi-modal verification system that integrates Generative Adversarial Networks (GANs), Reinforcement Learning (RL), and behavioral analysis to create adaptive challenges resistant to classical deep-learning attacks. Our system synthesizes unique visual stimuli via GAN-based generation alongside synchronized audio challenges, while an RL agent adjusts difficulty based on real-time user interaction patterns. A hybrid classifier combining heuristic rules and machine learning distinguishes human from bot interactions. We position Aura-CAPTCHA relative to well-established baselines (text-based schemes, Google reCAPTCHA v2, audio alternatives, and modern invisible risk-analysis systems) and evaluate it against documented state-of-the-art attacks, including convolutional-neural-network solvers, object-detection pipelines (YOLO), and recent agentic vision-language models. Experimental results indicate that Aura-CAPTCHA improves human success rates and lowers classical bypass rates compared to static challenge-based baselines, although, like all explicit-challenge systems, it remains vulnerable to emerging large-model agents. We discuss these limitations transparently and outline future directions toward cognitive-gap-based defenses.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2508.14976 [cs.LG] |
| (or arXiv:2508.14976v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2508.14976 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1007/978-981-95-0183-0_5
DOI(s) linking to related resources |
From: Joydeep Chandra [view email]
[v1]
Wed, 20 Aug 2025 18:00:08 UTC (1,642 KB)
[v2]
Tue, 5 May 2026 13:50:11 UTC (1,728 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。