4 papers
GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks
Canyixing Cui, Tao Wu, Xingping Xian +3
Graph Neural Networks (GNNs) are vulnerable to adversarial attacks, which inherently invert connectivity patterns by introducing disassortative edges in assortative graphs and asso…
Disentangled Graph Representation Based on Substructure-Aware Graph Optimal Matching Kernel Convolutional Networks
Mao Wang, Tao Wu, Xingping Xian +3
Graphs effectively characterize relational data, driving graph representation learning methods that uncover underlying predictive information. As state-of-the-art approaches, Graph…
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning
Tao Wu, Xinwen Cao, Chao Wang +5
Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial…
Understanding the Robustness of Graph Neural Networks against Adversarial Attacks
Tao Wu, Canyixing Cui, Xingping Xian +4
Recent studies have shown that graph neural networks (GNNs) are vulnerable to adversarial attacks, posing significant challenges to their deployment in safety-critical scenarios. T…