6 papers
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…
Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models
Yingsha Xie, Tiansheng Huang, Enneng Yang +5
Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually const…
Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
Yibo Wang, Tiansheng Huang, Li Shen +6
Harmful fine-tuning attack introduces significant security risks to the fine-tuning services. Main-stream defenses aim to vaccinate the model such that the later harmful fine-tunin…
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,…
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
Biao Yi, Tiansheng Huang, Baolei Zhang +4
Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradi…
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…