Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool

Graph Neural Networks (GNNs) have achieved significant success in various real-world applications, including social networks, finance systems, and traffic management. Recent researches highlight their vulnerability to backdoor attacks in node classification, where GNNs trained on a poisoned graph misclassify a test node only when specific triggers are attached. These studies typically focus on single attack categories and use adaptive trigger generators to create node-specific triggers. However, adaptive trigger generators typically have a simple structure, limited parameters, and lack category-aware graph knowledge, which makes them struggle to handle multi-category attacks effectively. We propose a multi-category graph backdoor attack framework with a subgraph triggers pool that achieves effective and unnoticeable attacks across multiple categories simultaneously.

Conference on Neural Information Processing Systems (NeurIPS 2025)