Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies

Abstract

Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks. As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability. Adversary can mislead GNNs to give wrong predictions by modifying the graph structure such as manipulating a few edges. This vulnerability has arisen tremendous concerns for adapting GNNs in safety-critical applications and has attracted increasing research attention in recent years. Thus, it is necessary and timely to provide a comprehensive overview of existing graph adversarial attacks and the countermeasures. In this survey, we categorize existing attacks and defenses, and review the corresponding state-of-the-art methods. Furthermore, we have developed a repository with representative algorithms (https://github.com/DSE-MSU/DeepRobust/tree/master/deeprobust/graph). The repository enables us to conduct empirical studies to deepen our understandings on attacks and defenses on graphs.

arXiv commentAccepted by SIGKDD Explorations

References in corpus (29)

• Semi-Supervised Classification with Graph Convolutional Networks
• Playing Atari with Deep Reinforcement Learning
• Neural Message Passing for Quantum Chemistry
• Axiomatic Attribution for Deep Networks
• Graph Neural Networks: A Review of Methods and Applications
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Adversarial Attacks on Neural Networks for Graph Data
• Certified Adversarial Robustness via Randomized Smoothing
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Adversarial Attack and Defense on Graph Data: A Survey
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Learning Discrete Structures for Graph Neural Networks
• Adversarial Attack on Graph Structured Data
• Fast Gradient Attack on Network Embedding
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• Attacking Graph Convolutional Networks via Rewiring
• Certifiable Robustness to Graph Perturbations
• Batch Virtual Adversarial Training for Graph Convolutional Networks
• Node Injection Attacks on Graphs via Reinforcement Learning
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
• Link Prediction Adversarial Attack
• GraphSAC: Detecting anomalies in large-scale graphs
• GraphDefense: Towards Robust Graph Convolutional Networks
• Can Adversarial Network Attack be Defended?
• Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
• DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder
• Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing

Cited by in corpus (16)

• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• To be Robust or to be Fair: Towards Fairness in Adversarial Training
• Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
• Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks
• Structack: Structure-based Adversarial Attacks on Graph Neural Networks
• USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
• Node Similarity Preserving Graph Convolutional Networks
• Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagation
• Adversarial Attacks on Graph Classification via Bayesian Optimisation
• Distributionally Robust Semi-Supervised Learning Over Graphs
• On the Stability of Graph Convolutional Neural Networks under Edge Rewiring
• Graph Feature Gating Networks
• Cross-Modality Protein Embedding for Compound-Protein Affinity and Contact Prediction
• Spatio-Temporal Sparsification for General Robust Graph Convolution Networks