Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language ModelsChia-yi HsuYu-Lin Tsaiet al.2024NeurIPS 2024
Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?Yu-Lin TsaiChia-yi Hsuet al.2024ICLR 2024
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method PerspectiveMing-yu ChungSheng-yen Chouet al.2024ICLR 2024