Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
This addresses a security vulnerability for GNN users in domains like classification tasks, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of detecting backdoor attacks in Graph Neural Networks (GNNs) by developing a novel method using graph-level explanations and seven new metrics, achieving high detection performance on multiple benchmark datasets.
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 effective detection techniques are lacking. 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. Additionally, we develop an adaptive attack to rigorously evaluate our approach. We test our method on multiple benchmark datasets and examine its efficacy against various attack models. Our results show that our method can achieve high detection performance, marking a significant advancement in safeguarding GNNs against backdoor attacks.