SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger.
Sunguk Shin, Fangzhao Wu, Byung-Jun Lee, Meeyoung Cha, Sungwon Park
Browse the full ACL paper archive.
Sunguk Shin, Fangzhao Wu, Byung-Jun Lee, Meeyoung Cha, Sungwon Park
Browse the full ACL paper archive.