E-SAGE: Explainability-based Defense Against Backdoor Attacks on Graph Neural Networks

arXiv:2406.10655v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) have recently been widely adopted in multiple domains. Yet, they are notably vulnerable to adversarial and backdoor attacks. In particular, backdoor attacks based on subgraph insertion have been shown to be effective in graph classification tasks while being stealthy, successfully circumventing various existing defense methods. In this paper, we propose E-SAGE, a novel approach to defending GNN backdoor attacks based on explainability. We find that the malicious edges and benign edges …

adversarial arxiv attacks backdoor backdoor attacks classification cs.cr defense domains explainability graph networks neural networks sage vulnerable