A paper accepted to Proceedings of the International Conference on Machine Learning (ICML), 2026
Embedded Files
Jailbreak to Protect: Buffering Harmful Fine-Tuning via Temporary Jailbreaking LoRA in Large Language Models (Spotlight top 2.2%)
Seokil Ham, Jaehyuk Jang, Wonjun Lee and Changick Kim
Page updated
Google Sites
Report abuse