Adversarial Attacks on Neural Networks for Graph Data
Deep learning models for graphs have achieved strong performance for the task of node classification. Despite their proliferation, currently there is no study of their robustness to adversarial attacks. Yet, in domains where they are likely to be used, e.g. the web, adversaries are common. Can deep learning models for graphs be easily fooled? In this work, we introduce the first study of adversarial attacks on attributed graphs, specifically focusing on models exploiting ideas of graph convolutions. In addition to attacks at test time, we tackle the more challenging class of poisoning/causative attacks, which focus on the training phase of a machine learning model. We generate adversarial perturbations targeting the node's features and the graph structure, thus, taking the dependencies between instances in account. Moreover, we ensure that the perturbations remain unnoticeable by preserving important data characteristics. To cope with the underlying discrete domain we propose an efficient algorithm Nettack exploiting incremental computations. Our experimental study shows that accuracy of node classification significantly drops even when performing only few perturbations. Even more, our attacks are transferable: the learned attacks generalize to other state-of-the-art node classification models and unsupervised approaches, and likewise are successful even when only limited knowledge about the graph is given.
Code (1)
Tasks
General ClassificationNode ClassificationSimilar Papers 제목 키워드 기반
Graph Structure Learning for Robust Graph Neural Networks
Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial att…
Graph Neural NetworkGraph structure learningRepresentation LearningLarge-Scale Adversarial Attacks on Graph Neural Networks via Graph Coarsening
Graph Neural Networks (GNNs) are fragile to adversarial attacks. However, existing state-of-the-art adversarial attack methods against GNNs are typically constrained by the graph's scale, failing to attack large graphs e…
Adversarial AttackIDEA: Invariant Defense for Graph Adversarial Robustness
Despite the success of graph neural networks (GNNs), their vulnerability to adversarial attacks poses tremendous challenges for practical applications. Existing defense methods suffer from severe performance decline unde…
Adversarial RobustnessAdversarial Attacks on Locally Private Graph Neural Networks
Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious concerns, especially when dealing with sensitive information. Local Di…
Adversarial RobustnessGraph Neural NetworkGraph LearningSimilarity Preserving Adversarial Graph Contrastive Learning
Recent works demonstrate that GNN models are vulnerable to adversarial attacks, which refer to imperceptible perturbation on the graph structure and node features. Among various GNN models, graph contrastive learning (GC…
Adversarial RobustnessContrastive Learning