DATABANK

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou, Caglar Gulcehre, Maksym Andriushchenko, Ameya Prabhu, Jonas Geiping

paper

controlprompt injection

Cite this paper

Credit the original research and its authors.

BibTeX
@misc{terekhov-2026-adaptive-attacks-on,
  author = {Mikhail Terekhov and Alexander Panfilov and Daniil Dzenhaliou and Caglar Gulcehre and Maksym Andriushchenko and Ameya Prabhu and Jonas Geiping},
  title = {{Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols}},
  year = {2026},
  note = {ICLR 2026},
  url = {https://arxiv.org/abs/2510.09462}
}