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

Understand

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.
• Recognizing the challenge in detecting such intrusions, we devised a novel detection method that creatively leverages graph-level explanations.
• By extracting and transforming secondary outputs from GNN explanation mechanisms, we developed seven innovative metrics for effective detection of backdoor attacks on GNNs.