3 papers
cs.LG2026
Gecko: Fast Private Inference via Secure Public Encoder Offloading
Cheng'an Wei, Kai Chen, Yue Zhao +2
Private inference protects both user inputs and server models during neural network inference, but existing solutions remain too slow for practical deployment. This motivates recen…
cs.CR2026
Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs
Yiyang Lu, Jinwen He, Yue Zhao +4
Large Language Models (LLMs) are increasingly deployed as multi-turn assistants and customized through instruction tuning with project-specific training components. This practice c…
cs.AI2024
Hidden in Plain Sight: Exploring Chat History Tampering in Interactive Language Models
Cheng'an Wei, Yue Zhao, Yujia Gong +3
Large Language Models (LLMs) such as ChatGPT and Llama have become prevalent in real-world applications, exhibiting impressive text generation performance. LLMs are fundamentally d…