Training AIs to Solve CAPTCHAs
New research demonstrates that vision-language models can learn to solve CAPTCHAs more efficiently over time, undermining a cornerstone of automated-abuse prevention that many European enterprises still rely on.
Summary written by editorial AI · Source link below
Interesting research : Abstract : Vision-language models (VLMs) can solve visual CAPTCHAs without task-specific training, but the agents built on them approach every challenge from scratch. For such an agent, the hundredth instance of a familiar puzzle costs as much time and compute as the first. Specialized detectors invert the trade-off, answering in milliseconds but only for categories they were trained on. Neither improves with exposure. We study what changes when a solver improves with use.
Editorial Analysis
As VLMs gain the ability to solve CAPTCHAs at scale with decreasing cost, enterprises dependent on CAPTCHA-based bot defences face rising fraud and credential-stuffing risk.
Audit web-facing applications for CAPTCHA reliance and plan migration to behavioural or risk-score-based bot mitigation.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at Schneier on Security in a new tab.
More from the Research Desk
- Signed, Sealed, and Relayed, NTLM-style: Bypassing LDAP Signing Through Reauthentication3d
- Not Where You Think: Protecting Location Privacy Against Reasoning-Based Geolocation4d
- Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure4d
- Practical Auditing of Differentially Private Graph Release Mechanisms: Methodology, Toolkit, and Case Study4d
- SecLog-Bench: A Scalable Benchmark for Cybersecurity Log Reasoning with Scaffolded Evidence4d