Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation. (arXiv:2312.17301v1 [cs.CR])

Despite the success of graph neural networks (GNNs) in various domains, they
exhibit susceptibility to adversarial attacks. Understanding these
vulnerabilities is crucial for developing robust and secure applications. In
this paper, we investigate the impact of test time adversarial attacks through
edge perturbations which involve both edge insertions and deletions. A novel
explainability-based method is proposed to identify important nodes in the
graph and perform edge perturbation between these nodes. The proposed method is
tested for node classification with three …

adversarial adversarial attacks applications attack attacks domains edge graph graphs impact networks neural networks test understanding vulnerabilities