A clean-label graph backdoor attack method in node classification task
Not on the map. Why?
Abstract (arXiv)
Backdoor attacks in the traditional graph neural networks (GNNs) field are easily detectable due to the dilemma of confusing labels. To explore the backdoor vulnerability of GNNs and create a more stealthy backdoor attack method, a clean-label graph backdoor attack method(CGBA) in the node classification task is proposed in this paper. Differently from existing backdoor attack methods, CGBA requires neither modification of node labels nor graph structure. Specifically, to solve the problem of inconsistency between the contents and labels of the samples, CGBA selects poisoning samples in a specific target class and uses the label of sample as the target label (i.e., clean-label) after injecting triggers into the target samples. To guarantee the similarity of neighboring nodes, the raw features of the nodes are elaborately picked as triggers to further improve the concealment of the triggers. Extensive experiments results show the effectiveness of our method. When the poisoning rate is 0.04, CGBA can achieve an average attack success rate of 87.8%, 98.9%, 89.1%, and 98.5%, respectively.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 30 Dec 2023.
Builds on
22 of 38 references.
References · 22
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
- 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
- 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
- 2019Graph Neural Networks with convolutional ARMA filterscited by 185
- 2020Backdoor Attacks to Graph Neural Networkscited by 128
- 2020Graph Backdoorcited by 112
- 2021FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysiscited by 61
- 2020ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Predictioncited by 58
10 more
- 2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
- 2021Explainability-based Backdoor Attacks Against Graph Neural Networkscited by 42
- 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
- 2021HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecastingcited by 22
- 2022Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifscited by 19
- 2022Link-Backdoor: Backdoor Attack on Link Prediction via Node Injectioncited by 10
- 2023PoisonedGNN: Backdoor Attack on Graph Neural Networks-based Hardware Security Systemscited by 10
- 2022Defending Against Backdoor Attack on Graph Nerual Network by Explainabilitycited by 9
- 2023A semantic backdoor attack against Graph Convolutional Networkscited by 8
- 2022Neighboring Backdoor Attacks on Graph Convolutional Networkcited by 7
Built on by
Citing papers per year: 2024: 5; 2025: 3; 2026: 2.
10 papers.
- 2024Robustness Inspired Graph Backdoor Defensecited by 7
- 2024Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attackscited by 5
- 2024Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directionscited by 4
- 2024AGSOA:Graph Neural Network Targeted Attack Based on Average Gradient and Structure Optimizationcited by 1
- 2024Backdoor Attack on Vertical Federated Graph Neural Network Learningcited by 1
- 2025CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networkscited by 1
- 2025HeteroBA: A Structure-Manipulating Backdoor Attack on Heterogeneous Graphscited by 0
- 2025HeteroHBA: A Generative Structure-Manipulating Backdoor Attack on Heterogeneous Graphscited by 0
- 2026BadImplant: Injection-based Multi-Targeted Graph Backdoor Attackcited by 0
- 2026Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attackscited by 0
- 2026Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks5 Mar 2026
- 2026BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack21 Jan 2026
- 2025HeteroHBA: A Generative Structure-Manipulating Backdoor Attack on Heterogeneous Graphs31 Dec 2025
- 2025CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks20 Jun 2025
- 2025HeteroBA: A Structure-Manipulating Backdoor Attack on Heterogeneous Graphs27 May 2025
- 2024Backdoor Attack on Vertical Federated Graph Neural Network Learning15 Oct 2024
- 2024Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks15 Jul 2024
- 2024AGSOA:Graph Neural Network Targeted Attack Based on Average Gradient and Structure Optimization19 Jun 2024
- 2024Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions15 Jun 2024
- 2024Robustness Inspired Graph Backdoor Defense14 Jun 2024
Similar, not cited
Close in wording, no citation either way
- 2024A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only
- 2025A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
- 2024Effective backdoor attack on graph neural networks in link prediction tasks
- 2025Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
- 2024Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
- 2025Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective
- 2023XGBD: Explanation-Guided Graph Backdoor Detection
- 2024DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks