Data to 14 Oct 2026

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective

arXiv 1906.04214 ↗First posted 10 Jun 2019cs.LG cs.CR cs.SIcited by 196

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of GNNs. In this paper, we first present a novel gradient-based attack method that facilitates the difficulty of tackling discrete graph data. When comparing to current adversarial attacks on GNNs, the results show that by only perturbing a small number of edge perturbations, including addition and deletion, our optimization-based attack can lead to a noticeable decrease in classification performance. Moreover, leveraging our gradient-based attack, we propose the first optimization-based adversarial training for GNNs. Our method yields higher robustness against both different gradient based and greedy attack methods without sacrificing classification accuracy on original graph.

Key facts. Cited by 196 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 29; 2022: 43; 2023: 34; 2024: 49; 2025: 29; 2026: 12.

196 papers.

Sort:

By area:

2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
2021Robustness of Graph Neural Networks at Scalecited by 100
2024Attacking Large Language Models with Projected Gradient Descentcited by 94
2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 67
2022Understanding and Improving Graph Injection Attack by Promoting Unnoticeabilitycited by 62
2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 62
2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
2021GraphMI: Extracting Private Graph Data from Graph Neural Networkscited by 50
2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50

38 more

2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
2024Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearningcited by 44
2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
2022Adversarial Graph Contrastive Learning with Information Regularizationcited by 38
2023Are Defenses for Graph Neural Networks Robust?cited by 38
2021Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustnesscited by 35
2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
2022DropMessage: Unifying Random Dropping for Graph Neural Networkscited by 29
2021Interpretable Stability Bounds for Spectral Graph Filterscited by 28
2023Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directionscited by 28
2021A Hard Label Black-box Adversarial Attack Against Graph Neural Networkscited by 26
2022EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networkscited by 26
2022Model Inversion Attacks against Graph Neural Networkscited by 26
2022Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagationcited by 25
2024Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?cited by 23
2021Generating Adversarial Computer Programs using Optimized Obfuscationscited by 22
2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
2022Model-Agnostic Augmentation for Accurate Graph Classificationcited by 21
2022Adversarial Weight Perturbation Improves Generalization in Graph Neural Networkscited by 21
2022TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimizationcited by 21
2021Adversarial Attack on Graph Neural Networks as An Influence Maximization Problemcited by 20
2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
2022Transferable Graph Backdoor Attackcited by 19
2022Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learningcited by 19
2023Revisiting Robustness in Graph Machine Learningcited by 19
2021Decentralized Inference with Graph Neural Networks in Wireless Communication Systemscited by 18
2021Jointly Attacking Graph Neural Network and its Explanationscited by 18
2022Structure-Preserving Graph Representation Learningcited by 17
2021SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluationcited by 16
2021Graph Structural Attack by Perturbing Spectral Distancecited by 16
2022Characterizing the Influence of Graph Elementscited by 16
2023Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debiascited by 16
2021CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networkscited by 15
2022Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophilycited by 15
2024Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptationcited by 15
2023A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacycited by 14
2024Cross-Context Backdoor Attacks against Graph Prompt Learningcited by 14

50 most cited of 196 All 196 (JSON)