Refusal Is Not an Option: Unlearning Safety Alignment of Large Language Models
No ratings
Presented at USENIX Security 2025 by
Safety alignment has become an indispensable procedure to ensure the safety of large language models (LLMs), as they are reported to generate harmful, privacy-sensitive, and copy-righted content when prompted with adversarial instructions. Machine unlearning is a representative approach to establishing the safety of LLMs, enabling them to forget problematic training instances and thereby minimize their influence. However, no prior study has investigated the feasibility of adversarial unlearning—using seemingly legitimate unlearning requests to compromise the safety of a target LLM.