mlsanityData to 7 Oct 2026

Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions

arXiv 2306.15427 ↗First posted 27 Jun 2023cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations. In the pursuit of fixing adversarial training (1) we show and overcome fundamental theoretical as well as practical limitations of the adopted graph learning setting in prior work; (2) we reveal that more flexible GNNs based on learnable graph diffusion are able to adjust to adversarial perturbations, while the learned message passing scheme is naturally interpretable; (3) we introduce the first attack for structure perturbations that, while targeting multiple nodes at once, is capable of handling global (graph-level) as well as local (node-level) constraints. Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

40 of 54 references.

References · 40

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  6. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  7. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  8. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  9. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  10. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  11. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  12. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
28 more
  1. 2018Adversarial Attack on Graph Structured Datacited by 300
  2. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  3. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  4. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  5. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  6. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  7. 2017Cooperative Game Theory Approaches for Network Partitioningcited by 134
  8. 2018Contextual Stochastic Block Modelscited by 134
  9. 2019Stability Properties of Graph Neural Networkscited by 125
  10. 2021Robustness of Graph Neural Networks at Scalecited by 100
  11. 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
  12. 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
  13. 2016Hiding Individuals and Communities in a Social Networkcited by 77
  14. 2019Certifiable Robustness to Graph Perturbationscited by 62
  15. 2022Understanding and Improving Graph Injection Attack by Promoting Unnoticeabilitycited by 62
  16. 2020Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and Morecited by 56
  17. 2021Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learningcited by 44
  18. 2020Reliable Graph Neural Networks via Robust Aggregationcited by 43
  19. 2023Are Defenses for Graph Neural Networks Robust?cited by 38
  20. 2021Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustnesscited by 35
  21. 2019Batch Virtual Adversarial Training for Graph Convolutional Networkscited by 33
  22. 2023Revisiting Robustness in Graph Machine Learningcited by 19
  23. 2023Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networkscited by 16
  24. 2022Spectral Adversarial Training for Robust Graph Neural Networkcited by 12
  25. 2023Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networkscited by 10
  26. 2022Analyzing Data-Centric Properties for Graph Contrastive Learningcited by 7
  27. 2020Towards an Efficient and General Framework of Robust Training for Graph Neural Networkscited by 6
  28. 2022Learning Robust Representation through Graph Adversarial Contrastive Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 12; 2025: 11.

28 papers.

Sort:

By area:

  1. 2024Attacking Large Language Models with Projected Gradient Descentcited by 91
  2. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  3. 2024Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?cited by 22
  4. 2025REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objectivecited by 15
  5. 2024Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNscited by 14
  6. 2023Hierarchical Randomized Smoothingcited by 9
  7. 2023Node-aware Bi-smoothing: Certified Robustness against Graph Injection Attackscited by 8
  8. 2024LLMPirate: LLMs for Black-box Hardware IP Piracycited by 7
  9. 2025Diffusion-based Adversarial Purification from the Perspective of the Frequency Domaincited by 7
  10. 2024AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learningcited by 6
  11. 2024Adversarial Training: A Surveycited by 6
  12. 2024Explainable Graph Neural Networks Under Firecited by 5
16 more
  1. 2024SafePowerGraph: Safety-aware Evaluation of Graph Neural Networks for Transmission Power Gridscited by 5
  2. 2025Robust Conformal Prediction with a Single Binary Certificatecited by 4
  3. 2025Exact Verification of Graph Neural Networks with Incremental Constraint Solvingcited by 4
  4. 2024Collective Certified Robustness against Graph Injection Attackscited by 3
  5. 2023On the Adversarial Robustness of Graph Contrastive Learning Methodscited by 2
  6. 2025Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defensescited by 2
  7. 2023Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustnesscited by 1
  8. 2024Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimizationcited by 1
  9. 2025Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defensescited by 1
  10. 2023Poisoning × Evasion: Symbiotic Adversarial Robustness for Graph Neural Networkscited by 0
  11. 2024Graph Adversarial Diffusion Convolutioncited by 0
  12. 2025Personalized Layer Selection for Graph Neural Networkscited by 0
  13. 2025Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentationscited by 0
  14. 2025EvA: Evolutionary Attacks on Graphscited by 0
  15. 2025Enhancing Graph Classification Robustness with Singular Poolingcited by 0
  16. 2025Topologically-Stabilized Graph Neural Networks: Empirical Robustness Across Domainscited by 0