Skip to yearly menu bar Skip to main content


Poster

Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence

Quoc Nguyen ⋅ Trung Le ⋅ Jing Wu ⋅ Anh Bui ⋅ Mehrtash Harandi
2026 Poster

Abstract

Video

Chat is not available.