@article{modeltamperingattacksenablemorerigorous,
  title = {Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities},
  author = {Zora Che and Stephen Casper and Robert Kirk and Anirudh Satheesh and Stewart Slocum and Lev E McKinney and Rohit Gandikota and Aidan Ewart and Domenic Rosati and Zichu Wu and Zikui Cai and Bilal Chughtai and Yarin Gal and Furong Huang and Dylan Hadfield-Menell},
  year = {2025},
  eprint = {2502.05209},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.05209v2},
}