@article{detectingadversarialfinetuningwithauditi, title = {Detecting Adversarial Fine-tuning with Auditing Agents}, author = {Sarah Egler and John Schulman and Nicholas Carlini}, year = {2025}, eprint = {2510.16255}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.16255}, }