3 papers
cs.CR2023
Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networks
Binghui Wang, Meng Pang, Yun Dong
Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph learning tasks. However, recent studies show that GNNs are vulnerable to both test-time evasio…
cs.CR2020
Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs
Houxiang Fan, Binghui Wang, Pan Zhou +6
Link prediction in dynamic graphs (LPDG) is an important research problem that has diverse applications such as online recommendations, studies on disease contagion, organizational…
cs.CR2020
Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
Binghui Wang, Tianxiang Zhou, Minhua Lin +5
Graph neural network (GNN), the mainstream method to learn on graph data, is vulnerable to graph evasion attacks, where an attacker slightly perturbing the graph structure can fool…