4 papers
Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs
Zihui Chen, Yuling Wang, Pengfei Jiao +4
Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node. While boosting expressiveness, they also expose ne…
DP-DGAD: A Generalist Dynamic Graph Anomaly Detector with Dynamic Prototypes
Jialun Zheng, Jie Liu, Jiannong Cao +4
Dynamic graph anomaly detection (DGAD) is essential for identifying anomalies in evolving graphs across domains such as finance, traffic, and social networks. Recently, generalist…
HeTa: Relation-wise Heterogeneous Graph Foundation Attack Model
Yuling Wang, Zihui Chen, Pengfei Jiao +1
Heterogeneous Graph Neural Networks (HGNNs) are vulnerable, highlighting the need for tailored attacks to assess their robustness and ensure security. However, existing HGNN attack…
Addressing Graph Heterogeneity and Heterophily from A Spectral Perspective
Kangkang Lu, Yanhua Yu, Zhiyong Huang +6
Graph neural networks (GNNs) have demonstrated excellent performance in semi-supervised node classification tasks. Despite this, two primary challenges persist: heterogeneity and h…