On the Adversarial Robustness of Graph Neural Networks with Graph Reduction

TL;DR

This paper empirically investigates how graph reduction techniques like coarsening and sparsification affect the adversarial robustness of GNNs, revealing that sparsification can sometimes improve robustness while coarsening often worsens it.

Contribution

It provides a comprehensive empirical analysis of the impact of graph reduction methods on GNN adversarial robustness, including new insights into their contrasting effects.

Findings

Sparsification can reduce attack effectiveness for some methods.

Coarsening generally increases vulnerability to attacks.

Analysis offers practical guidance for robust GNN design.

Abstract

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 scalability remains underexplored. In this paper, we present an extensive empirical study to investigate the impact of graph reduction techniques, specifically graph coarsening and sparsification, on the robustness of GNNs against adversarial attacks. Through extensive experiments involving multiple datasets and GNN architectures, we examine the effects of four sparsification and six coarsening methods on the poisoning attacks. Our results indicate that, while graph sparsification can mitigate the effectiveness of certain poisoning attacks, such as Mettack, it has limited impact on others, like PGD. Conversely, graph coarsening tends to amplify the adversarial impact, significantly reducing classification accuracy as the reduction ratio decreases. Additionally, we provide a novel analysis of the causes driving these effects and examine how defensive GNN models perform under graph reduction, offering practical insights for designing robust GNNs within graph acceleration systems.