Robustness-Inspired Defense Against Backdoor Attacks on Graph Neural Networks

arXiv:2406.09836v1 Announce Type: cross
Abstract: Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significant threat to their real-world adoption. Despite initial efforts to defend against specific graph backdoor attacks, there is no work on defending against various types of backdoor attacks where generated triggers have different properties. Hence, we first empirically verify that prediction variance under edge dropping …

adoption arxiv attacks backdoor backdoor attacks classification cs.cr cs.lg defense graph networks neural networks node real results reveal robustness studies threat vulnerable world