HeteroBA: A Structure-Manipulating Backdoor Attack on Heterogeneous Graphs
This work addresses security vulnerabilities in HGNNs used in domains like recommendation and finance, highlighting potential threats from backdoor attacks, though it is incremental as it applies known attack concepts to a new graph type.
The paper tackles the problem of backdoor attacks on heterogeneous graph neural networks (HGNNs) by proposing HeteroBA, a framework that inserts trigger nodes to cause misclassification of specific nodes into a target label while maintaining accuracy on clean data, achieving high attack success rates with minimal impact on clean accuracy in experiments on three datasets and various HGNN architectures.
Heterogeneous graph neural networks (HGNNs) have recently drawn increasing attention for modeling complex multi-relational data in domains such as recommendation, finance, and social networks. While existing research has been largely focused on enhancing HGNNs' predictive performance, their robustness and security, especially under backdoor attacks, remain underexplored. In this paper, we propose a novel Heterogeneous Backdoor Attack (HeteroBA) framework for node classification tasks on heterogeneous graphs. HeteroBA inserts carefully crafted trigger nodes with realistic features and targeted structural connections, leveraging attention-based and clustering-based strategies to select influential auxiliary nodes for effective trigger propagation, thereby causing the model to misclassify specific nodes into a target label while maintaining accuracy on clean data. Experimental results on three datasets and various HGNN architectures demonstrate that HeteroBA achieves high attack success rates with minimal impact on the clean accuracy. Our method sheds light on potential vulnerabilities in HGNNs and calls for more robust defenses against backdoor threats in multi-relational graph scenarios.