Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics

ArXi:2403.18136v3 Announce Type: replace-cross Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their performance and ethical application. The detection of these attacks is crucial for maintaining the reliability and security of GNN classification tasks, but existing methods are often inflexible, relying on single metrics that fail to capture the full range of backdoor behaviors.