mlsanityData to 14 Oct 2026

Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation

arXiv 2605.05534 ↗First posted 7 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial learning and the robustness of Graph Neural Networks (GNNs) are topics of widespread interest in the machine learning community, as documented by the number of adversarial attacks and defenses designed for these purposes. While a rigorous evaluation of these adversarial methods is necessary to understand the robustness of GNNs in real-world applications, we posit that many works in the literature do not share the same experimental settings, leading to ambiguous and potentially contradictory scientific conclusions. In this benchmark, we demonstrate the importance of adopting fair, robust, and standardized evaluation protocols in adversarial GNN research. We perform a comprehensive re-evaluation of seven widely used attacks and eight recent defenses under both poisoning and evasion scenarios, across six popular graph datasets. Our study spans over 453,000 experiments conducted within a unified framework. We observe substantial differences in adversarial attack performance when evaluated under a fair and robust procedure. Our findings reveal that previously overlooked factors, such as target node selection and the training process of the attacked model, have a profound impact on attack effectiveness, to the extent of completely distorting performance insights. These results underscore the urgent need for standardized evaluations in adversarial graph machine learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 70 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

41 of 70 references.

References · 41

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  4. 2019Simplifying Graph Convolutional Networkscited by 1,477
  5. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  6. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  7. 2019Multi-scale Attributed Node Embeddingcited by 548
  8. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  9. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  10. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  11. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  12. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
29 more
  1. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  2. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  3. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  4. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  5. 2018Troubling Trends in Machine Learning Scholarshipcited by 108
  6. 2019A Gentle Introduction to Deep Learning for Graphscited by 108
  7. 2021Robustness of Graph Neural Networks at Scalecited by 100
  8. 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
  9. 2020DeepRobust: A PyTorch Library for Adversarial Attacks and Defensescited by 78
  10. 2021Elastic Graph Neural Networkscited by 67
  11. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 67
  12. 2018Fast Gradient Attack on Network Embeddingcited by 65
  13. 2021Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learningcited by 44
  14. 2020Adversarial Attack on Large Scale Graphcited by 39
  15. 2023Are Defenses for Graph Neural Networks Robust?cited by 38
  16. 2021Understanding Structural Vulnerability in Graph Convolutional Networkscited by 37
  17. 2019Batch Virtual Adversarial Training for Graph Convolutional Networkscited by 33
  18. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  19. 2020Unsupervised Adversarially-Robust Representation Learning on Graphscited by 17
  20. 2022Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervisioncited by 16
  21. 2020Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attackscited by 15
  22. 2020Adversarial Immunization for Certifiable Robustness on Graphscited by 14
  23. 2022GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networkscited by 14
  24. 2024A Simple and Yet Fairly Effective Defense for Graph Neural Networkscited by 12
  25. 2020Tensor Graph Convolutional Networks for Multi-relational and Robust Learningcited by 9
  26. 2024Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attackscited by 9
  27. 2023Robust Graph Neural Networks via Unbiased Aggregationcited by 8
  28. 2019Edge Dithering for Robust Adaptive Graph Convolutional Networkscited by 2
  29. 2025If You Want to Be Robust, Be Wary of Initializationcited by 1

Built on by

Not cited yet.