AI RESEARCH

Universal Graph Backdoor Defense: A Feature-based Homophily Perspective

arXiv CS.LG

ArXi:2605.16815v1 Announce Type: cross Graph neural networks (GNNs) have achieved remarkable success in relational learning. However, their vulnerability to graph backdoor attacks (GBAs) poses a significant barrier to broader adoption in high-stakes applications. Despite recent advances in graph backdoor defense (GBD), existing methods primarily focus on subgraph-based GBAs, relying on the assumption that poisoned target nodes are explicitly connected to subgraph triggers.