Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
This work addresses fairness issues in GNNs for researchers and practitioners, highlighting a realistic attack scenario that is incremental by extending existing attacks to node injections.
The paper tackles the problem of fairness vulnerabilities in Graph Neural Networks (GNNs) by introducing a node injection-based attack (NIFA) that significantly undermines fairness, achieving this by injecting only 1% of nodes across three real-world datasets.
Despite the remarkable capabilities demonstrated by Graph Neural Networks (GNNs) in graph-related tasks, recent research has revealed the fairness vulnerabilities in GNNs when facing malicious adversarial attacks. However, all existing fairness attacks require manipulating the connectivity between existing nodes, which may be prohibited in reality. To this end, we introduce a Node Injection-based Fairness Attack (NIFA), exploring the vulnerabilities of GNN fairness in such a more realistic setting. In detail, NIFA first designs two insightful principles for node injection operations, namely the uncertainty-maximization principle and homophily-increase principle, and then optimizes injected nodes' feature matrix to further ensure the effectiveness of fairness attacks. Comprehensive experiments on three real-world datasets consistently demonstrate that NIFA can significantly undermine the fairness of mainstream GNNs, even including fairness-aware GNNs, by injecting merely 1% of nodes. We sincerely hope that our work can stimulate increasing attention from researchers on the vulnerability of GNN fairness, and encourage the development of corresponding defense mechanisms. Our code and data are released at: https://github.com/CGCL-codes/NIFA.