mlsanityData to 7 Oct 2026

Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies

arXiv 2003.00653 ↗First posted 2 Mar 2020cs.LG cs.CR stat.MLcited by 42

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks. As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability. Adversary can mislead GNNs to give wrong predictions by modifying the graph structure such as manipulating a few edges. This vulnerability has arisen tremendous concerns for adapting GNNs in safety-critical applications and has attracted increasing research attention in recent years. Thus, it is necessary and timely to provide a comprehensive overview of existing graph adversarial attacks and the countermeasures. In this survey, we categorize existing attacks and defenses, and review the corresponding state-of-the-art methods. Furthermore, we have developed a repository with representative algorithms (https://github.com/DSE-MSU/DeepRobust/tree/master/deeprobust/graph). The repository enables us to conduct empirical studies to deepen our understandings on attacks and defenses on graphs.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 19; 2022: 11; 2023: 4; 2024: 7; 2025: 1.

42 papers.

Sort:

By area:

  1. 2021Trustworthy AI: A Computational Perspectivecited by 93
  2. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  3. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  4. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  5. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  6. 2021Single Node Injection Attack against Graph Neural Networkscited by 45
  7. 2021Understanding Structural Vulnerability in Graph Convolutional Networkscited by 37
  8. 2022Model Inversion Attacks against Graph Neural Networkscited by 26
  9. 2022Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagationcited by 25
  10. 2021Adversarial Attack on Graph Neural Networks as An Influence Maximization Problemcited by 20
  11. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  12. 2021Decentralized Inference with Graph Neural Networks in Wireless Communication Systemscited by 18
30 more
  1. 2021Jointly Attacking Graph Neural Network and its Explanationscited by 18
  2. 2021Towards Robust Graph Contrastive Learningcited by 16
  3. 2021CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networkscited by 15
  4. 2022Spectral Adversarial Training for Robust Graph Neural Networkcited by 12
  5. 2022Adversarial Camouflage for Node Injection Attack on Graphscited by 11
  6. 2022Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attackcited by 10
  7. 2021Distributionally Robust Semi-Supervised Learning Over Graphscited by 9
  8. 2024Collaboration! Towards Robust Neural Methods for Routing Problemscited by 9
  9. 2021Structack: Structure-based Adversarial Attacks on Graph Neural Networkscited by 8
  10. 2022Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classificationcited by 8
  11. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  12. 2021Adversarial Attacks on Graph Classification via Bayesian Optimisationcited by 5
  13. 2023IDEA: Invariant Defense for Graph Adversarial Robustnesscited by 4
  14. 2024SAGMAN: Stability Analysis of Graph Neural Networks on the Manifoldscited by 4
  15. 2024Rethinking Independent Cross-Entropy Loss For Graph-Structured Datacited by 4
  16. 2021Reinforcement Learning For Data Poisoning on Graph Neural Networkscited by 3
  17. 2021Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defensecited by 3
  18. 2021Graph Feature Gating Networkscited by 3
  19. 2024You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learningcited by 3
  20. 2023Graph Adversarial Immunization for Certifiable Robustnesscited by 2
  21. 2021Adversarial Robustness of Probabilistic Network Embedding for Link Predictioncited by 1
  22. 2023Sparse but Strong: Crafting Adversarially Robust Graph Lottery Ticketscited by 1
  23. 2024GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximizationcited by 1
  24. 2021Spatio-Temporal Sparsification for General Robust Graph Convolution Networkscited by 0
  25. 2021Inference Attacks Against Graph Neural Networkscited by 0
  26. 2022Robust, Deep, and Reinforcement Learning for Management of Communication and Power Networkscited by 0
  27. 2022Are All Edges Necessary? A Unified Framework for Graph Purificationcited by 0
  28. 2024Perseus: Leveraging Common Data Patterns with Curriculum Learning for More Robust Graph Neural Networkscited by 0
  29. 2024Normalized Space Alignment: A Versatile Metric for Representation Analysiscited by 0
  30. 2025Topologically-Stabilized Graph Neural Networks: Empirical Robustness Across Domainscited by 0