Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
Binghui Wang, Minhua Lin, Tianxiang Zhou, Pan Zhou, Ang Li, Meng Pang, Hai Helen Li, Yiran Chen · 2024
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 trained GNN models. Existing work has at least one of the following drawbacks: 1) limited to directly attack two-layer GNNs; 2) inefficient; and 3) impractical, as they need to know full or part of GNN model parameters.