CoG: a Two-View Co-training Framework for Defending Adversarial Attacks on Graph

Abstract

Graph neural networks exhibit remarkable performance in graph data analysis. However, the robustness of GNN models remains a challenge. As a result, they are not reliable enough to be deployed in critical applications. Recent studies demonstrate that GNNs could be easily fooled with adversarial perturbations, especially structural perturbations. Such vulnerability is attributed to the excessive dependence on the structure information to make predictions. To achieve better robustness, it is desirable to build the prediction of GNNs with more comprehensive features. Graph data, in most cases, has two views of information, namely structure information and feature information. In this paper, we propose CoG, a simple yet effective co-training framework to combine these two views for the purpose of robustness. CoG trains sub-models from the feature view and the structure view independently and allows them to distill knowledge from each other by adding their most confident unlabeled data into the training set. The orthogonality of these two views diversifies the sub-models, thus enhancing the robustness of their ensemble. We evaluate our framework on three popular datasets, and results show that CoG significantly improves the robustness of graph models against adversarial attacks without sacrificing their performance on clean data. We also show that CoG still achieves good robustness when both node features and graph structures are perturbed.

References in corpus (13)

• Inductive Representation Learning on Large Graphs
• Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
• Adversarial Attacks on Neural Networks for Graph Data
• The Space of Transferable Adversarial Examples
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Improving Adversarial Robustness via Promoting Ensemble Diversity
• Adversarial Attacks on Node Embeddings via Graph Poisoning
• Improving Adversarial Robustness of Ensembles with Diversity Training
• Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
• Learning to Drop: Robust Graph Neural Network via Topological Denoising
• Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks