OffensiveAIcon highlights: ExploitBench debut and fully autonomous HTTP attack cascade
dyn___ · x · 2026-10-06
Attendees pick their favorite talks at OffensiveAIcon: Dr. Brumley introduced AI quantification/benchmarking and unveiled ExploitBench; @dyn demoed offensive models for variant analysis of security patches; @albinowax walked through building a fully autonomous HTTP offensive cascade, with nuance on cascade model design. Offensive AI engineering is maturing fast.
More from Safety
- Apollo Research CEO: even perfect safety testing wouldn't have caught OpenAI's HF hack — MariusHobbhahn · 2026-10-06
- Do Agent Swarms Amplify Unethical Behavior? HF Attack Chatlogs Spark Peer-Pressure Debate — Bloated_Plaid · 2026-10-06
- Why OpenAI's Regulatory Nightmare Is Only Getting Started — pstAsiatech · 2026-10-06
- StealthGPT Launches Super 'Humanizer' Model, Claims It Beat AI Detector Pangram — menhguin · 2026-10-06
- Axios scoop: OpenAI, Anthropic probing tens of thousands of frontier model misbehavior incidents — Miles_Brundage · 2026-10-06
- Pentagon walks back AI polygraph trustworthiness analysis after criticism — hoofnagle · 2026-10-06