Large-Scale Adversarial Attacks on Graph Neural Networks via Graph Coarsening
Graph Neural Networks (GNNs) are fragile to adversarial attacks. However, existing state-of-the-art adversarial attack methods against GNNs are typically constrained by the graph's scale, failing to attack large graphs effectively. In this paper, we propose a novel attack method that attacks the graph in a divide-and-conquer manner to tackle large-scale adversarial attacks on GNNs. Specifically, the nodes are clustered based on node embeddings, coarsened graphs are constructed using the node clusters, and attacks are conducted on the coarsened graphs. Perturbations are selected starting with smaller coarsened graphs and progressing to larger detailed graphs while most of the irrelative nodes remain clustered, significantly reducing the complexity of generating adversarial graphs. Extensive empirical results show that the proposed method can greatly save the computational resources required to attack GNNs on large graphs while maintaining comparable performance on small graphs.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
Talos: A More Effective and Efficient Adversarial Defense for GNN Models Based on the Global Homophily of Graphs
Graph neural network (GNN) models play a pivotal role in numerous tasks involving graph-related data analysis. Despite their efficacy, similar to other deep learning models, GNNs are susceptible to adversarial attacks. E…
Adversarial DefenseGraph Neural NetworkGraph structure learningUnderstanding the Impact of Graph Reduction on Adversarial Robustness in Graph Neural Networks
As Graph Neural Networks (GNNs) become increasingly popular for learning from large-scale graph data across various domains, their susceptibility to adversarial attacks when using graph reduction techniques for scalabili…
Adversarial RobustnessGARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data. However, recent studies show that GNNs are vulnerable to graph adversarial attacks. Althou…
Adversarial RobustnessRobustness of Graph Neural Networks at Scale
Graph Neural Networks (GNNs) are increasingly important given their popularity and the diversity of applications. Yet, existing studies of their vulnerability to adversarial attacks rely on relatively small graphs. We ad…
DiversityUnderstanding the Robustness of Graph Neural Networks against Adversarial Attacks
Recent studies have shown that graph neural networks (GNNs) are vulnerable to adversarial attacks, posing significant challenges to their deployment in safety-critical scenarios. This vulnerability has spurred a growing …
Adversarial Robustness