Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation.
Danny Halawi, Alexander Wei, Eric Wallace, Tony Tong Wang, Nika Haghtalab, Jacob Steinhardt
Browse the full ICML paper archive.
Danny Halawi, Alexander Wei, Eric Wallace, Tony Tong Wang, Nika Haghtalab, Jacob Steinhardt
Browse the full ICML paper archive.