A backdoor attack against link prediction tasks with graph neural networks. (arXiv:2401.02663v1 [cs.LG])

Graph Neural Networks (GNNs) are a class of deep learning models capable of
processing graph-structured data, and they have demonstrated significant
performance in a variety of real-world applications. Recent studies have found
that GNN models are vulnerable to backdoor attacks. When specific patterns
(called backdoor triggers, e.g., subgraphs, nodes, etc.) appear in the input
data, the backdoor embedded in the GNN models is activated, which misclassifies
the input data into the target class label specified by the attacker, whereas
when …

applications attack attacks backdoor backdoor attacks called class data deep learning found graph link networks neural networks patterns performance prediction real structured data studies vulnerable world