一作ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
Mikhail Terekhov · Alexander Panfilov · Daniil Dzenhaliou · Caglar Gulcehre · Maksym Andriushchenko · Ameya Prabhu · Jonas Geiping