Exploiting Meta-Learning-based Poisoning Attacks for Graph Link Prediction
This addresses a security problem for applications like recommendation systems and social networks, but it is incremental as it focuses on a less-studied aspect of GNN robustness.
The paper tackles the vulnerability of Graph Neural Networks (GNNs) in link prediction to adversarial attacks by introducing a meta-learning-based poisoning attack that degrades performance, showing it significantly reduces link prediction accuracy and outperforms existing methods.
Link prediction in graph data uses various algorithms and Graph Nerual Network (GNN) models to predict potential relationships between graph nodes. These techniques have found widespread use in numerous real-world applications, including recommendation systems, community/social networks, and biological structures. However, recent research has highlighted the vulnerability of GNN models to adversarial attacks, such as poisoning and evasion attacks. Addressing the vulnerability of GNN models is crucial to ensure stable and robust performance in GNN applications. Although many works have focused on enhancing the robustness of node classification on GNN models, the robustness of link prediction has received less attention. To bridge this gap, this article introduces an unweighted graph poisoning attack that leverages meta-learning with weighted scheme strategies to degrade the link prediction performance of GNNs. We conducted comprehensive experiments on diverse datasets across multiple link prediction applications to evaluate the proposed method and its parameters, comparing it with existing approaches under similar conditions. Our results demonstrate that our approach significantly reduces link prediction performance and consistently outperforms other state-of-the-art baselines.