activity
20242026
collaborators

5 papers

cs.LG2026

Differentially Private Natural Gradient Descent

Pan Li, Kai Chen, Shuai Chang +3

Under a fixed privacy budget, the utility of differentially private (DP) training is ultimately determined by its optimization efficiency. Standard first-order DP optimizers such a…

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.CR2025

PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty

Jinwen He, Yiyang Lu, Zijin Lin +2

Large Language Models (LLMs) are widely used in sensitive domains, including healthcare, finance, and legal services, raising concerns about potential private information leaks dur…

cs.CL2024

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis

Jinwen He, Yujia Gong, Kai Chen +3

Large Language Models (LLMs) have revolutionized various domains with extensive knowledge and creative capabilities. However, a critical issue with LLMs is their tendency to produc…

cs.CR2024

I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectors

Zijin Lin, Yue Zhao, Kai Chen +1

Deep neural networks (DNNs) have revolutionized the field of computer vision like object detection with their unparalleled performance. However, existing research has shown that DN…