3 papers
cs.AI2026
Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink
Guozhi Liu, Weiwei Lin, Tiansheng Huang +4
Harmful fine-tuning can invalidate safety alignment of large language models, exposing significant safety risks. In this paper, we utilize the attention sink mechanism to mitigate…
cs.CR2025
Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
Guozhi Liu, Qi Mu, Tiansheng Huang +4
Harmful fine-tuning issues present significant safety challenges for fine-tuning-as-a-service in large language models. Existing alignment-stage defenses, e.g., Vaccine, Repnoise,…
cs.LG2025
Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation
Guozhi Liu, Weiwei Lin, Tiansheng Huang +3
Harmful fine-tuning attack poses a serious threat to the online fine-tuning service. Vaccine, a recent alignment-stage defense, applies uniform perturbation to all layers of embedd…