FBA: Fairness Backdoor Attack on Graph Neural Networks

Minghao Xu, Fengrui Hao, Tianlong Gu, Ming Liu

Abstract: Graph neural networks (GNNs) are a set of methods that aim to apply deep neural networks to graph-structured data. Despite their promising performance on various graph analysis tasks, they might have discrimination towards certain populations when exploited in human-centered applications without fairness considerations. Moreover, extant studies have shown that GNNs are vulnerable to backdoor attacks, through which malicious users can degrade the predication performance of GNNs. Nevertheless, attacks to the fairness of GNNs are still unexplored. In this article, we analyze the limitations of existing GNNs backdoor attacks, and propose a novel fairness backdoor attack (FBA) method for GNNs. First, we provide the candidate space selection mechanism to select the fair node candidate space using the long-tail distribution, which facilitates the subsequent generation of triggers. Second, we develop the trigger generation strategy to generate fairness triggers by quantifying the deviations between different groups of sensitive attributes, enabling the attack to degrade the fairness almost without affecting the accuracy. Finally, we undertake extensive evaluation experiments on real datasets and state-of-the-art models to demonstrate the effectiveness of the FBA method, including five mainstream models (GCN, GraphSAGE, GAT, GAE, and VGAE), three downstream tasks (node classification, graph classification and link prediction), and two fair GNNs (NIFTY and Fairedit).

External IDs:dblp:journals/tdsc/XuHGL25