mlsanityData to 14 Oct 2026

Jointly Attacking Graph Neural Network and its Explanations

arXiv 2108.03388 ↗First posted 7 Aug 2021cs.LG cs.AI cs.CRcited by 18

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have boosted the performance for many graph-related tasks. Despite the great success, recent studies have shown that GNNs are highly vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs. On the other hand, the explanation of GNNs (GNNExplainer) provides a better understanding of a trained GNN model by generating a small subgraph and features that are most influential for its prediction. In this paper, we first perform empirical studies to validate that GNNExplainer can act as an inspection tool and have the potential to detect the adversarial perturbations for graphs. This finding motivates us to further initiate a new problem investigation: Whether a graph neural network and its explanations can be jointly attacked by modifying graphs with malicious desires? It is challenging to answer this question since the goals of adversarial attacks and bypassing the GNNExplainer essentially contradict each other. In this work, we give a confirmative answer to this question by proposing a novel attack framework (GEAttack), which can attack both a GNN model and its explanations by simultaneously exploiting their vulnerabilities. Extensive experiments on two explainers (GNNExplainer and PGExplainer) under various real-world datasets demonstrate the effectiveness of the proposed method.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 48 of its 69 references that are in the map. First posted on arXiv 7 Aug 2021.

Builds on

48 of 69 references.

References · 48

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  8. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  9. 2019Heterogeneous Graph Attention Networkcited by 734
  10. 2019Graph Neural Networks for Social Recommendationcited by 714
  11. 2017Interpretation of Neural Networks is Fragilecited by 444
  12. 2020Parameterized Explainer for Graph Neural Networkcited by 426
36 more
  1. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  2. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  3. 2018Adversarial Attack on Graph Structured Datacited by 301
  4. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  5. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  6. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
  7. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  8. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  9. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  10. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  11. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  12. 2020Debugging Tests for Model Explanationscited by 147
  13. 2020Adversarial Self-Supervised Contrastive Learningcited by 139
  14. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  15. 2019Fooling Neural Network Interpretations via Adversarial Model Manipulationcited by 112
  16. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  17. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  18. 2021Trustworthy AI: A Computational Perspectivecited by 93
  19. 2019Does Gender Matter? Towards Fairness in Dialogue Systemscited by 89
  20. 2020DeepRobust: A PyTorch Library for Adversarial Attacks and Defensescited by 78
  21. 2020Towards More Practical Adversarial Attacks on Graph Neural Networkscited by 76
  22. 2018Interpretable Deep Learning under Firecited by 74
  23. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  24. 2021Elastic Graph Neural Networkscited by 67
  25. 2018Fast Gradient Attack on Network Embeddingcited by 65
  26. 2018Graph-to-Sequence Learning using Gated Graph Neural Networkscited by 61
  27. 2019Attacking Graph-based Classification via Manipulating the Graph Structurecited by 53
  28. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  29. 2020Interpretation of NLP models through input marginalizationcited by 44
  30. 2020Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studiescited by 42
  31. 2020FIND: Human-in-the-Loop Debugging Deep Text Classifierscited by 40
  32. 2019Attacking Graph Convolutional Networks via Rewiringcited by 32
  33. 2019Deep Social Collaborative Filteringcited by 32
  34. 2020Attacking Black-box Recommendations via Copying Cross-domain User Profilescited by 31
  35. 2021AutoLoss: Automated Loss Function Search in Recommendationscited by 31
  36. 2019Deep Adversarial Social Recommendationcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 2; 2024: 5; 2025: 1; 2026: 3.

18 papers.

Sort:

By area:

  1. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
  2. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  3. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  4. 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 81
  5. 2021Graph Trend Filtering Networks for Recommendationscited by 53
  6. 2024Graph Machine Learning in the Era of Large Language Models (LLMs)cited by 33
  7. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  8. 2022Disentangled Contrastive Learning for Social Recommendationcited by 27
  9. 2022Knowledge-enhanced Black-box Attacks for Recommendationscited by 26
  10. 2024Graph Unlearning with Efficient Partial Retrainingcited by 20
  11. 2022Private Graph Extraction via Feature Explanationscited by 16
  12. 2024Explainable Graph Neural Networks Under Firecited by 5
6 more
  1. 2025iTFKAN: Interpretable Time Series Forecasting with Kolmogorov-Arnold Networkcited by 2
  2. 2026ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networkscited by 2
  3. 2024Stability of Explainable Recommendationcited by 0
  4. 2024Robust Explainable Recommendationcited by 0
  5. 2026Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attackscited by 0
  6. 2026Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networkscited by 0