Evaluating Frontier AI Agents As Autonomous Clinical Security Auditors

Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical expertise, specialized tools, and significant time. We present an open evaluation task, built on METR Task Standard v0.3.0, that tests whether frontier ...

Advancing Cybersecurity in the Age of Frontier AI: Qualys Steps into Project Glasswing

The cybersecurity industry has spent much of the last two years debating how attackers might use AI. That debate matters, but it misses a larger point: defenders now have an opportunity to change the economics of cyber risk. For me, the question is not whether AI will influence cybersecurity. It...

Asymmetry by Design: Boosting Cyber Defenders with Differential Access to AI

As AI-enabled cyber capabilities become more advanced, we propose "differential access" as a strategy to tilt the cybersecurity balance toward defense by shaping access to these capabilities. We introduce three possible approaches that form a continuum, becoming progressively more restrictive for...