Unveiling the Threat: Investigating Distributed and Centralized Backdoor Attacks in Federated Graph Neural Networks

Graph Neural Networks (GNNs) have gained significant popularity as powerful deep learning methods for processing graph data. However, centralized GNNs face challenges in data-sensitive scenarios due to privacy concerns and regulatory restrictions. Federated learning (FL) has emerged as a promising technology that enables collaborative training of a shared global model while preserving privacy. While FL has been applied to train GNNs, no research focuses on the robustness of Federated GNNs against backdoor attacks. This paper bridges this research gap by investigating two types of backdoor attacks in Federated GNNs: centralized backdoor attacks (CBA) and distributed backdoor attacks (DBA). Through extensive experiments, we demonstrate that DBA exhibits a higher success rate than CBA across various scenarios. To further explore the characteristics of these backdoor attacks in Federated GNNs, we evaluate their performance under different scenarios, including varying numbers of clients, trigger sizes, poisoning intensities, and trigger densities. Additionally, we explore the resilience of DBA and CBA against two defense mechanisms. Our findings reveal that both defenses can not eliminate DBA and CBA without affecting the original task. This highlights the necessity of developing tailored defenses to mitigate the novel threat of backdoor attacks in Federated GNNs.