Exploiting Meta-Learning-based Poisoning Attacks for Graph Link Prediction

2025-04-08

AI Summary

Variational Graph Autoencoders (VGAEs) lack robustness evaluation against adversarial structural poisoning attacks in link prediction—a critical yet underexplored gap. Method: We propose the first meta-learning–based (MAML) unweighted graph structure poisoning attack, operating in a black-box setting that optimizes minimal edge perturbations without accessing model weights. Our approach jointly performs adversarial optimization and discrete edge-level search, achieving high efficiency, cross-model transferability, and low query cost—overcoming limitations of gradient-based or heuristic alternatives. Contribution/Results: On benchmark citation networks (Cora, Citeseer, Pubmed), our attack reduces VGAE’s AUC by 15–32%, significantly outperforming state-of-the-art methods including FGA and NETTACK. This work establishes a novel paradigm for evaluating robustness of graph neural networks under structural adversarial perturbations.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Link prediction in graph data utilizes various algorithms and machine learning/deep learning models to predict potential relationships between graph nodes. This technique has found widespread use in numerous real-world applications, including recommendation systems, community networks, and biological structures. However, recent research has highlighted the vulnerability of link prediction models to adversarial attacks, such as poisoning and evasion attacks. Addressing the vulnerability of these models is crucial to ensure stable and robust performance in link prediction applications. While many works have focused on enhancing the robustness of the Graph Convolution Network (GCN) model, the Variational Graph Auto-Encoder (VGAE), a sophisticated model for link prediction, has not been thoroughly investigated in the context of graph adversarial attacks. To bridge this gap, this article proposes an unweighted graph poisoning attack approach using meta-learning techniques to undermine VGAE's link prediction performance. We conducted comprehensive experiments on diverse datasets to evaluate the proposed method and its parameters, comparing it with existing approaches in similar settings. Our results demonstrate that our approach significantly diminishes link prediction performance and outperforms other state-of-the-art methods.

Problem

• Investigates VGAE vulnerability to poisoning attacks
• Proposes meta-learning-based attack on link prediction
• Evaluates attack effectiveness across diverse datasets

Innovation

• Meta-learning-based poisoning attack on VGAE
• Unweighted graph poisoning for link prediction
• Outperforms state-of-the-art adversarial methods