mlsanityData to 7 Oct 2026

Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics

arXiv 2403.18136 ↗First posted 26 Mar 2024cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their performance and ethical application. The detection of these attacks is crucial for maintaining the reliability and security of GNN classification tasks, but existing methods are often inflexible, relying on single metrics that fail to capture the full range of backdoor behaviors. Recognizing the challenge in detecting such intrusions, we devised a novel detection method that creatively leverages graph-level explanations. By extracting and transforming secondary outputs from GNN explanation mechanisms, we developed seven innovative metrics for effective detection of backdoor attacks on GNNs. Additionally, we develop an adaptive attack to rigorously evaluate our approach. We test our method on multiple benchmark datasets and examine its efficacy against various attack models. Our results show that our method can achieve high detection performance, marking a significant advancement in safeguarding GNNs against backdoor attacks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 41 of its 69 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

41 of 69 references.

References · 41

  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. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  7. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  8. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  9. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  10. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  11. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  12. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
29 more
  1. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  2. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 258
  3. 2020Loss landscapes and optimization in over-parameterized non-linear systems and neural networkscited by 231
  4. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 203
  5. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 162
  6. 2017Neural Trojanscited by 151
  7. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  8. 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 120
  9. 2020RAB: Provable Robustness Against Backdoor Attackscited by 115
  10. 2020Graph Backdoorcited by 112
  11. 2020Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Casescited by 93
  12. 2021BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Modelscited by 76
  13. 2020On Certifying Robustness against Backdoor Attacks via Randomized Smoothingcited by 74
  14. 2021Triggerless Backdoor Attack for NLP Tasks with Clean Labelscited by 61
  15. 2023Reconstructive Neuron Pruning for Backdoor Defensecited by 56
  16. 2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
  17. 2021Explainability-based Backdoor Attacks Against Graph Neural Networkscited by 42
  18. 2021Clustering by Maximizing Mutual Information Across Viewscited by 23
  19. 2022Transferable Graph Backdoor Attackcited by 19
  20. 2022Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifscited by 19
  21. 2024A comprehensive study on fidelity metrics for XAIcited by 14
  22. 2024Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistencycited by 13
  23. 2024Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlationscited by 12
  24. 2022Defending Against Backdoor Attack on Graph Nerual Network by Explainabilitycited by 9
  25. 2023PoisonedGNN: Backdoor Attack on Graph Neural Networks-based Hardware Security Systemscited by 9
  26. 2023MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systemscited by 8
  27. 2023XGBD: Explanation-Guided Graph Backdoor Detectioncited by 6
  28. 2020Backdoor Smoothing: Demystifying Backdoor Attacks on Deep Neural Networkscited by 5
  29. 2023Towards Understanding How Self-training Tolerates Data Backdoor Poisoningcited by 4

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directionscited by 4
  2. 2024Efficient and Robust Continual Graph Learning for Graph Classification in Biologycited by 3
  3. 2025Watermarking Graph Neural Networks via Explanations for Ownership Protectioncited by 3
  4. 2025Backdoor Attacks on Discrete Graph Diffusion Modelscited by 3
  5. 2024Defense-as-a-Service: Black-box Shielding against Backdoored Graph Modelscited by 0
  6. 2024DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networkscited by 0