2 papers
cs.LG2026
IMU: Influence-guided Machine Unlearning
Xindi Fan, Jing Wu, Mingyi Zhou +3
Machine Unlearning (MU) aims to selectively erase the influence of specific data points from pretrained models. However, most existing MU methods rely on the retain set to preserve…
cs.LG2026
Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
Quoc Minh Nguyen, Trung Le, Jing Wu +2
Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as…