Understanding the Robustness of Graph Neural Networks against Adversarial Attacks
Not on the map. Why?
Abstract (arXiv)
Recent studies have shown that graph neural networks (GNNs) are vulnerable to adversarial attacks, posing significant challenges to their deployment in safety-critical scenarios. This vulnerability has spurred a growing focus on designing robust GNNs. Despite this interest, current advancements have predominantly relied on empirical trial and error, resulting in a limited understanding of the robustness of GNNs against adversarial attacks. To address this issue, we conduct the first large-scale systematic study on the adversarial robustness of GNNs by considering the patterns of input graphs, the architecture of GNNs, and their model capacity, along with discussions on sensitive neurons and adversarial transferability. This work proposes a comprehensive empirical framework for analyzing the adversarial robustness of GNNs. To support the analysis of adversarial robustness in GNNs, we introduce two evaluation metrics: the confidence-based decision surface and the accuracy-based adversarial transferability rate. Through experimental analysis, we derive 11 actionable guidelines for designing robust GNNs, enabling model developers to gain deeper insights. The code of this study is available at https://github.com/star4455/GraphRE.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 62 references that are in the map. First posted on arXiv 20 Jun 2024.
Builds on
42 of 62 references.
References · 42
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
- 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
- 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
- 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
- 2018Adversarial Attack on Graph Structured Datacited by 301
30 more
- 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
- 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
- 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
- 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
- 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
- 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
- 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
- 2020Design Space for Graph Neural Networkscited by 182
- 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
- 2021Robustness of Graph Neural Networks at Scalecited by 100
- 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
- 2021TDGIA:Effective Injection Attacks on Graph Neural Networkscited by 67
- 2021Elastic Graph Neural Networkscited by 67
- 2018Fast Gradient Attack on Network Embeddingcited by 65
- 2019Transferring Robustness for Graph Neural Network Against Poisoning Attackscited by 58
- 2019Attacking Graph-based Classification via Manipulating the Graph Structurecited by 53
- 2023Are Defenses for Graph Neural Networks Robust?cited by 38
- 2021Understanding Structural Vulnerability in Graph Convolutional Networkscited by 37
- 2019Batch Virtual Adversarial Training for Graph Convolutional Networkscited by 33
- 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
- 2022Anomal-E: A Self-Supervised Network Intrusion Detection System based on Graph Neural Networkscited by 27
- 2023The Expressive Power of Graph Neural Networks: A Surveycited by 27
- 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
- 2022Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learningcited by 19
- 2023TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Supportcited by 12
- 2019Virtual Adversarial Training on Graph Convolutional Networks in Node Classificationcited by 11
- 2020Tensor Graph Convolutional Networks for Multi-relational and Robust Learningcited by 9
- 2022FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classificationcited by 7
- 2023Node Injection for Class-specific Network Poisoningcited by 5
- 2023Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learningcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.