Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
Paper
•
2510.09462
•
Published
•
5
Daniil Dzenhaliou
programmer228
AI & ML interests
None yet
Recent Activity
authored
a paper
21 days ago
INCLUDE: Evaluating Multilingual Language Understanding with Regional
Knowledge
authored
a paper
21 days ago
Apertus: Democratizing Open and Compliant LLMs for Global Language
Environments
authored
a paper
21 days ago
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
Organizations
None yet
upvoted
a
paper
21 days ago