2 papers
cs.CL2024
Course-Correction: Safety Alignment Using Synthetic Preferences
Rongwu Xu, Yishuo Cai, Zhenhong Zhou +6
The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability…
cs.CR2024
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
Boheng Li, Yishuo Cai, Haowei Li +3
Model quantization is widely used to compress and accelerate deep neural networks. However, recent studies have revealed the feasibility of weaponizing model quantization via impla…