A Survey of Adversarial Learning on Graphs

Abstract

Deep learning models on graphs have achieved remarkable performance in various graph analysis tasks, e.g., node classification, link prediction, and graph clustering. However, they expose uncertainty and unreliability against the well-designed inputs, i.e., adversarial examples. Accordingly, a line of studies has emerged for both attack and defense addressed in different graph analysis tasks, leading to the arms race in graph adversarial learning. Despite the booming works, there still lacks a unified problem definition and a comprehensive review. To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically. Specifically, we survey and unify the existing works w.r.t. attack and defense in graph analysis tasks, and give appropriate definitions and taxonomies at the same time. Besides, we emphasize the importance of related evaluation metrics, investigate and summarize them comprehensively. Hopefully, our works can provide a comprehensive overview and offer insights for the relevant researchers. Latest advances in graph adversarial learning are summarized in our GitHub repository https://github.com/EdisonLeeeee/Graph-Adversarial-Learning.

arXiv commentPreprint; 16 pages, 2 figures

References in corpus (30)

• Finding and evaluating community structure in networks
• Intriguing properties of neural networks
• Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
• Link Prediction in Complex Networks: A Survey
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Achieving Human Parity in Conversational Speech Recognition
• Dynamic Graph Convolutional Networks
• Adversarial Personalized Ranking for Recommendation
• 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
• Adversarial Attack on Graph Structured Data
• Fast Gradient Attack on Network Embedding
• Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
• Attacking Graph Convolutional Networks via Rewiring
• Attack Graph Convolutional Networks by Adding Fake Nodes
• Batch Virtual Adversarial Training for Graph Convolutional Networks
• Data Poisoning Attack against Unsupervised Node Embedding Methods
• Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure
• Link Prediction Adversarial Attack
• GraphDefense: Towards Robust Graph Convolutional Networks
• GraphSAC: Detecting anomalies in large-scale graphs
• Can Adversarial Network Attack be Defended?
• Adversarial Defense Framework for Graph Neural Network
• Time-aware Gradient Attack on Dynamic Network Link Prediction
• Attack Tolerance of Link Prediction Algorithms: How to Hide Your Relations in a Social Network
• Edge Dithering for Robust Adaptive Graph Convolutional Networks
• Multiscale Evolutionary Perturbation Attack on Community Detection
• Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling
• Adversarial Recommendation: Attack of the Learned Fake Users

Cited by in corpus (15)

• A Comprehensive Survey on Deep Graph Representation Learning
• Adversarial Attack and Defense on Graph Data: A Survey
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• Single Node Injection Attack against Graph Neural Networks
• Node-Level Membership Inference Attacks Against Graph Neural Networks
• A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks
• NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data
• Projective Ranking-based GNN Evasion Attacks
• USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
• Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
• Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense
• GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software
• Adversarial Attack on Large Scale Graph
• I-GCN: Robust Graph Convolutional Network via Influence Mechanism
• DeepInsight: Interpretability Assisting Detection of Adversarial Samples on Graphs