IDEA: Invariant Defense for Graph Adversarial Robustness

arXiv:2305.15792v2 Announce Type: replace
Abstract: Despite the success of graph neural networks (GNNs), their vulnerability to adversarial attacks poses tremendous challenges for practical applications. Existing defense methods suffer from severe performance decline under unseen attacks, due to either limited observed adversarial examples or pre-defined heuristics. To address these limitations, we analyze the causalities in graph adversarial attacks and conclude that causal features are key to achieve graph adversarial robustness, owing to their determinedness for labels and invariance across attacks. To …

adversarial arxiv cs.cr cs.lg defense graph robustness type