mlsanityData to 14 Oct 2026

MADE: Graph Backdoor Defense with Masked Unlearning

arXiv 2411.18648 ↗First posted 26 Nov 2024cs.CR cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have garnered significant attention from researchers due to their outstanding performance in handling graph-related tasks, such as social network analysis, protein design, and so on. Despite their widespread application, recent research has demonstrated that GNNs are vulnerable to backdoor attacks, implemented by injecting triggers into the training datasets. Trained on the poisoned data, GNNs will predict target labels when attaching trigger patterns to inputs. This vulnerability poses significant security risks for applications of GNNs in sensitive domains, such as drug discovery. While there has been extensive research into backdoor defenses for images, strategies to safeguard GNNs against such attacks remain underdeveloped. Furthermore, we point out that conventional backdoor defense methods designed for images cannot work well when directly implemented on graph data. In this paper, we first analyze the key difference between image backdoor and graph backdoor attacks. Then we tackle the graph defense problem by presenting a novel approach called MADE, which devises an adversarial mask generation mechanism that selectively preserves clean sub-graphs and further leverages masks on edge weights to eliminate the influence of triggers effectively. Extensive experiments across various graph classification tasks demonstrate the effectiveness of MADE in significantly reducing the attack success rate (ASR) while maintaining a high classification accuracy.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 39 of its 53 references that are in the map. First posted on arXiv 26 Nov 2024.

Builds on

39 of 53 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2017Graph Attention Networkscited by 8,923
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  7. 2017Inductive Representation Learning on Large Graphscited by 6,320
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  9. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  10. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  11. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  12. 2015Gated Graph Sequence Neural Networkscited by 796
27 more
  1. 2019Graph Neural Networks for Social Recommendationcited by 714
  2. 2019Neural Graph Collaborative Filteringcited by 661
  3. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  4. 2018Spectral Signatures in Backdoor Attackscited by 484
  5. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  6. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  7. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 263
  8. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
  9. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 235
  10. 2019A backdoor attack against LSTM-based text classification systemscited by 227
  11. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  12. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  13. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 169
  14. 2020Graph Information Bottleneckcited by 168
  15. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  16. 2022Backdoor Defense via Decoupling the Training Processcited by 153
  17. 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 134
  18. 2020Backdoor Attacks to Graph Neural Networkscited by 128
  19. 2020Graph Backdoorcited by 112
  20. 2021Few-shot Backdoor Defense Using Shapley Estimationcited by 41
  21. 2022Rethinking the Reverse-engineering of Trojan Triggerscited by 39
  22. 2022Fine-Tuning Is All You Need to Mitigate Backdoor Attackscited by 38
  23. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  24. 2022Transferable Graph Backdoor Attackcited by 19
  25. 2022SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendationcited by 16
  26. 2022Defending Against Backdoor Attack on Graph Nerual Network by Explainabilitycited by 9
  27. 2022Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Biascited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesicscited by 17

Similar, not cited

Close in wording, no citation either way

  1. 2024Effective backdoor attack on graph neural networks in link prediction tasks
  2. 2024Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions
  3. 2024A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only
  4. 2023Unnoticeable Backdoor Attacks on Graph Neural Networks
  5. 2022Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs
  6. 2025Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective
  7. 2021Explainability-based Backdoor Attacks Against Graph Neural Networks
  8. 2024Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective