When can we trust untrusted monitoring? A safety case sketch across collusion strategies

Nelson Gardner-Challis, Jonathan Bostock, Georgiy Kozhevnikov, Morgan Sinclaire, Joan Velja, Alessandro Abate, Charlie Griffin

paper code

control steganography

Cite this paper

Credit the original research and its authors.

BibTeX

@misc{gardnerchallis-2026-when-can-we,
  author = {Nelson Gardner-Challis and Jonathan Bostock and Georgiy Kozhevnikov and Morgan Sinclaire and Joan Velja and Alessandro Abate and Charlie Griffin},
  title = {{When can we trust untrusted monitoring? A safety case sketch across collusion strategies}},
  year = {2026},
  note = {arXiv preprint},
  url = {https://arxiv.org/abs/2602.20628}
}