3 papers
cs.AI2026
FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs
Zhengyi Jin, Ru Zhang, Xiao Chen +5
Fragmented safety evaluation undermines the governance of dangerous AI capabilities. We present a modular framework that evaluates each model through three orthogonal pipelines---K…
cs.CR2026
EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning
Tianyun Zhang, Zhen Yang, Haozhao Wang +2
Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed threshold…
cs.CV2024
Pseudo-label Based Domain Adaptation for Zero-Shot Text Steganalysis
Yufei Luo, Zhen Yang, Ru Zhang +1
Currently, most methods for text steganalysis are based on deep neural networks (DNNs). However, in real-life scenarios, obtaining a sufficient amount of labeled stego-text for cor…