3 papers
cs.CL2025
MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security
Yanrui Du, Fenglei Fan, Sendong Zhao +3
As Large Language Models (LLMs) increasingly permeate human life, their security has emerged as a critical concern, particularly their ability to maintain harmless responses to mal…
cs.CL2025
Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
Yanrui Du, Fenglei Fan, Sendong Zhao +6
Instruction Fine-Tuning (IFT) has been widely adopted as an effective post-training strategy to enhance various abilities of Large Language Models (LLMs). However, prior studies ha…
cs.CL2025
Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
Yanrui Du, Sendong Zhao, Jiawei Cao +6
Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted signific…