3 papers
cs.LG2026
DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation
Yingxu Wang, Kunyu Zhang, Jiaxin Huang +4
Graph domain adaptation (GDA) aims to transfer knowledge from a labeled source graph to an unlabeled target graph under distribution shifts. However, existing methods are largely f…
cs.CR2026
What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models
Md Tasnim Jawad, Mingyan Xiao, Yanzhao Wu
With the widespread adoption of Large Language Models (LLMs) and increasingly stringent privacy regulations, protecting data privacy in LLMs has become essential, especially for pr…
cs.LG2025
DuSEGO: Dual Second-order Equivariant Graph Ordinary Differential Equation
Yingxu Wang, Nan Yin, Mingyan Xiao +3
Graph Neural Networks (GNNs) with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressivene…