5 papers
Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education
Xin Yi, Yue Li, Dongsheng Shi +3
Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise s…
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
Yue Li, Xin Yi, Dongsheng Shi +3
With the increasing size of Large Vision-Language Models (LVLMs), network pruning techniques aimed at compressing models for deployment in resource-constrained environments have ga…
Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation
Xin Yi, Yue Li, Shunfan Zheng +3
Watermarking has emerged as a critical technique for combating misinformation and protecting intellectual property in large language models (LLMs). A recent discovery, termed water…
Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
Xin Yi, Yue Li, Dongsheng Shi +3
Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable adva…
NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
Xin Yi, Shunfan Zheng, Linlin Wang +3
The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate…