papers

Publications (5)

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…

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.CV2024

Medical Visual Prompting (MVP): A Unified Framework for Versatile and High-Quality Medical Image Segmentation

Yulin Chen, Guoheng Huang, Kai Huang +5

Accurate segmentation of lesion regions is crucial for clinical diagnosis and treatment across various diseases. While deep convolutional networks have achieved satisfactory result…

cond-mat.dis-nn2025

Hidden self-duality and exact mobility edges in quasiperiodic network models

Hai-Tao Hu, Xiaoshui Lin, Ai-Min Guo +3

In one-dimensional quasiperiodic systems, only a few models with exact mobility edges (MEs) have been constructed using generalized self-duality theory, Avila's global theory, or t…

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…