2 papers
cs.CR2026
StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents
Ads Dawson, Adrian Wood
Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectabl…
cs.CR2026
Large Empirical Case Study: Go-Explore adapted for AI Red Team Testing
Manish Bhatt, Adrian Wood, Idan Habler +1
Production LLM agents with tool-using capabilities require security testing despite their safety training. We adapt Go-Explore to evaluate GPT-4o-mini across 28 experimental runs s…