FBA: Fairness Backdoor Attack on Graph Neural Networks
- 23 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (5) , 5813-5820
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 paper, we analyze the limitations of existing GNNs backdoor attacks, and propose a novel fairness backdoor attack (FBA) method for GNNs. Firstly, 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. Secondly, 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).Keywords
Funding Information
- National Natural Science Foundation of China (U22A2099, 62336003)
This publication has 32 references indexed in Scilit:
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and ExplainabilityMachine Intelligence Research, 2024
- Link-Backdoor: Backdoor Attack on Link Prediction via Node InjectionIEEE Transactions on Computational Social Systems, 2023
- Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks2022
- Cure-GNN: A Robust Curvature-Enhanced Graph Neural Network Against Adversarial AttacksIEEE Transactions on Dependable and Secure Computing, 2022
- A Weighted Symmetric Graph Embedding Approach for Link Prediction in Undirected GraphsIEEE Transactions on Cybernetics, 2022
- On the Fairness of Time-Critical Influence Maximization in Social Networks (Extended Abstract)2022
- Semisupervised Graph Neural Networks for Graph ClassificationIEEE Transactions on Cybernetics, 2022
- Poisoning Attacks on Fair Machine Learning2022
- Poisoning Attacks on Algorithmic Fairness2021
- Graph neural networks: A review of methods and applicationsAI Open, 2020