mlsanityData to 7 Oct 2026

Explainability-based Backdoor Attacks Against Graph Neural Networks

arXiv 2104.03674 ↗First posted 8 Apr 2021cs.LG cs.CRcited by 42

Not on the map. Why?

Abstract (arXiv)

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already numerous works on backdoor attacks on neural networks, but only a few works consider graph neural networks (GNNs). As such, there is no intensive research on explaining the impact of trigger injecting position on the performance of backdoor attacks on GNNs. To bridge this gap, we conduct an experimental investigation on the performance of backdoor attacks on GNNs. We apply two powerful GNN explainability approaches to select the optimal trigger injecting position to achieve two attacker objectives -- high attack success rate and low clean accuracy drop. Our empirical results on benchmark datasets and state-of-the-art neural network models demonstrate the proposed method's effectiveness in selecting trigger injecting position for backdoor attacks on GNNs. For instance, on the node classification task, the backdoor attack with trigger injecting position selected by GraphLIME reaches over 84 % attack success rate with less than 2.5 % accuracy drop

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

16 of 26 references.

References · 16

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  9. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  11. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  12. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
4 more
  1. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 158
  2. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  3. 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
  4. 2020Graph Backdoorcited by 112

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 10; 2024: 11; 2025: 4; 2026: 2.

42 papers.

Sort:

By area:

  1. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  2. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  3. 2022Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesiscited by 59
  4. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 41
  5. 2024Threats, Attacks, and Defenses in Machine Unlearning: A Surveycited by 34
  6. 2021Watermarking Graph Neural Networks based on Backdoor Attackscited by 25
  7. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  8. 2022SoK: Explainable Machine Learning for Computer Security Applicationscited by 20
  9. 2022Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifscited by 19
  10. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  11. 2022More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networkscited by 15
  12. 2023Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysiscited by 14
30 more
  1. 2021Accumulative Poisoning Attacks on Real-time Datacited by 10
  2. 2022Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attackcited by 10
  3. 2022Link-Backdoor: Backdoor Attack on Link Prediction via Node Injectioncited by 10
  4. 2023A clean-label graph backdoor attack method in node classification taskcited by 10
  5. 2022Defending Against Backdoor Attack on Graph Nerual Network by Explainabilitycited by 9
  6. 2023SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classificationcited by 6
  7. 2023XGBD: Explanation-Guided Graph Backdoor Detectioncited by 6
  8. 2024Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metricscited by 6
  9. 2021Adversarial Attacks on Graph Classification via Bayesian Optimisationcited by 5
  10. 2024Backdoor Graph Condensationcited by 5
  11. 2021Dyn-Backdoor: Backdoor Attack on Dynamic Link Predictioncited by 4
  12. 2023Rethinking the Trigger-injecting Position in Graph Backdoor Attackcited by 4
  13. 2023Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Networkcited by 4
  14. 2023Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Modelscited by 4
  15. 2024Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directionscited by 4
  16. 2021EGC2: Enhanced Graph Classification with Easy Graph Compressioncited by 3
  17. 2024GENIE: Watermarking Graph Neural Networks for Link Predictioncited by 3
  18. 2025Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Modelscited by 3
  19. 2024Krait: A Backdoor Attack Against Graph Prompt Tuningcited by 2
  20. 2024Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformerscited by 2
  21. 2025Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classificationcited by 2
  22. 2023Explainability-Based Adversarial Attack on Graphs Through Edge Perturbationcited by 1
  23. 2024Effective backdoor attack on graph neural networks in link prediction taskscited by 1
  24. 2024A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Onlycited by 1
  25. 2024Defense-as-a-Service: Black-box Shielding against Backdoored Graph Modelscited by 0
  26. 2024DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networkscited by 0
  27. 2025Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networkscited by 0
  28. 2025Heterogeneous Graph Backdoor Attackcited by 0
  29. 2026Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attackscited by 0
  30. 2026Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoorscited by 0