mlsanityData to 7 Oct 2026

Adversarial Attacks on Graph Neural Networks via Meta Learning

arXiv 1902.08412 ↗First posted 22 Feb 2019cs.LG cs.CR stat.MLcited by 261

Not on the map. Why?

Abstract (arXiv)

Deep learning models for graphs have advanced the state of the art on many tasks. Despite their recent success, little is known about their robustness. We investigate training time attacks on graph neural networks for node classification that perturb the discrete graph structure. Our core principle is to use meta-gradients to solve the bilevel problem underlying training-time attacks, essentially treating the graph as a hyperparameter to optimize. Our experiments show that small graph perturbations consistently lead to a strong decrease in performance for graph convolutional networks, and even transfer to unsupervised embeddings. Remarkably, the perturbations created by our algorithm can misguide the graph neural networks such that they perform worse than a simple baseline that ignores all relational information. Our attacks do not assume any knowledge about or access to the target classifiers.

Key facts. Cited by 261 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 56; 2022: 65; 2023: 45; 2024: 48; 2025: 32; 2026: 15.

261 papers.

Sort:

By area:

  1. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  2. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  3. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  4. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  5. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  6. 2021Robustness of Graph Neural Networks at Scalecited by 100
  7. 2021Trustworthy AI: A Computational Perspectivecited by 93
  8. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  9. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  10. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  11. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  12. 2021Towards Self-Explainable Graph Neural Networkcited by 75
38 more
  1. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  2. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  3. 2021TDGIA:Effective Injection Attacks on Graph Neural Networkscited by 67
  4. 2021Elastic Graph Neural Networkscited by 67
  5. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  6. 2021Few-shot Network Anomaly Detection via Cross-network Meta-learningcited by 64
  7. 2022Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labelscited by 63
  8. 2021Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyondcited by 62
  9. 2022Understanding and Improving Graph Injection Attack by Promoting Unnoticeabilitycited by 62
  10. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  11. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
  12. 2021A Value-Function-based Interior-point Method for Non-convex Bi-level Optimizationcited by 60
  13. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57
  14. 2021Automated Self-Supervised Learning for Graphscited by 50
  15. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  16. 2023GSLB: The Graph Structure Learning Benchmarkcited by 49
  17. 2021Single Node Injection Attack against Graph Neural Networkscited by 45
  18. 2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
  19. 2021Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learningcited by 44
  20. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 41
  21. 2022Adversarial Graph Contrastive Learning with Information Regularizationcited by 38
  22. 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 38
  23. 2023Are Defenses for Graph Neural Networks Robust?cited by 38
  24. 2021Understanding Structural Vulnerability in Graph Convolutional Networkscited by 37
  25. 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
  26. 2021On the Convergence Theory for Hessian-Free Bilevel Algorithmscited by 33
  27. 2022On the Robustness of Graph Neural Diffusion to Topology Perturbationscited by 30
  28. 2023OpenGSL: A Comprehensive Benchmark for Graph Structure Learningcited by 30
  29. 2023Kairos: Practical Intrusion Detection and Investigation using Whole-system Provenancecited by 30
  30. 2021A General Descent Aggregation Framework for Gradient-based Bi-level Optimizationcited by 28
  31. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  32. 2022Augmentations in Hypergraph Contrastive Learning: Fabricated and Generativecited by 28
  33. 2023Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directionscited by 28
  34. 2022EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networkscited by 26
  35. 2022Model Inversion Attacks against Graph Neural Networkscited by 26
  36. 2023Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexitycited by 26
  37. 2022Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagationcited by 25
  38. 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25

50 most cited of 261 All 261 (JSON)