Skip to content
InfoResearchPeer-reviewed

One Trigger, Multiple Victims: Clean-Label Neighborhood Backdoor Attacks on Graph Neural Networks

Published
Record updated
View JSON

Summary

This paper proposes a clean-label backdoor attack on Graph Neural Networks that injects a single trigger node attached to a target node. The attack misclassifies the target and its one-hop neighbors as the target class without changing their features or labels. Across multiple real-world benchmarks and mainstream GNN architectures, the authors report over 95% attack success rate on target nodes and their neighbors in most settings, including under state-of-the-art defenses.