mlsanityData to 14 Oct 2026

Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learning

arXiv 2110.06468 ↗First posted 13 Oct 2021cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Graph neural network (GNN) has achieved great success on graph representation learning. Challenged by large scale private data collected from user-side, GNN may not be able to reflect the excellent performance, without rich features and complete adjacent relationships. Addressing the problem, vertical federated learning (VFL) is proposed to implement local data protection through training a global model collaboratively. Consequently, for graph-structured data, it is a natural idea to construct a GNN based VFL framework, denoted as GVFL. However, GNN has been proved vulnerable to adversarial attacks. Whether the vulnerability will be brought into the GVFL has not been studied. This is the first study of adversarial attacks on GVFL. A novel adversarial attack method is proposed, named Graph-Fraudster. It generates adversarial perturbations based on the noise-added global node embeddings via the privacy leakage and the gradient of pairwise node. Specifically, first, Graph-Fraudster steals the global node embeddings and sets up a shadow model of the server for the attack generator. Second, noise is added into node embeddings to confuse the shadow model. At last, the gradient of pairwise node is used to generate attacks with the guidance of noise-added node embeddings. Extensive experiments on five benchmark datasets demonstrate that Graph-Fraudster achieves the state-of-the-art attack performance compared with baselines in different GNN based GVFLs. Furthermore, Graph-Fraudster can remain a threat to GVFL even if two possible defense mechanisms are applied. Additionally, some suggestions are put forward for the future work to improve the robustness of GVFL. The code and datasets can be downloaded at https://github.com/hgh0545/Graph-Fraudster.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 29 of its 48 references that are in the map. First posted on arXiv 13 Oct 2021.

Builds on

29 of 48 references.

References · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2019Simplifying Graph Convolutional Networkscited by 1,477
  5. 2019Deep Leakage from Gradientscited by 1,021
  6. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  7. 2019Agnostic Federated Learningcited by 456
  8. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  9. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  10. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  11. 2018Adversarial Attack on Graph Structured Datacited by 301
  12. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 204
17 more
  1. 2021Federated Learning for Open Bankingcited by 141
  2. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  3. 2021Label Leakage and Protection in Two-party Split Learningcited by 90
  4. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  5. 2018Fast Gradient Attack on Network Embeddingcited by 65
  6. 2020GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphscited by 64
  7. 2020Vertically Federated Graph Neural Network for Privacy-Preserving Node Classificationcited by 61
  8. 2020Adversarial Attack on Large Scale Graphcited by 39
  9. 2020FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selectioncited by 36
  10. 2020ASFGNN: Automated Separated-Federated Graph Neural Networkcited by 36
  11. 2019Attacking Graph Convolutional Networks via Rewiringcited by 32
  12. 2018Attack Graph Convolutional Networks by Adding Fake Nodescited by 26
  13. 2020FedNER: Privacy-preserving Medical Named Entity Recognition with Federated Learningcited by 24
  14. 2021A Vertical Federated Learning Framework for Graph Convolutional Networkcited by 21
  15. 2018GA Based Q-Attack on Community Detectioncited by 13
  16. 2020PrivacyFL: A simulator for privacy-preserving and secure federated learningcited by 12
  17. 2021Privacy-Preserving Federated Learning on Partitioned Attributescited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

17 papers.

Sort:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  2. 2022Federated Graph Neural Networks: Overview, Techniques and Challengescited by 52
  3. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  4. 2022Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applicationscited by 14
  5. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  6. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  7. 2023Vertical Federated Learning: Taxonomies, Threats, and Prospectscited by 8
  8. 2023Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaborationcited by 6
  9. 2023Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Networkcited by 4
  10. 2024Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligencecited by 3
  11. 2025Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defensescited by 3
  12. 2023Label Inference Attacks against Node-level Vertical Federated GNNscited by 1
5 more
  1. 2024Backdoor Attack on Vertical Federated Graph Neural Network Learningcited by 1
  2. 2025VGFL-SA: Vertical Graph Federated Learning Structure Attack Based on Contrastive Learningcited by 1
  3. 2026Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learningcited by 1
  4. 2024SpreadFGL: Edge-Client Collaborative Federated Graph Learning with Adaptive Neighbor Generationcited by 0
  5. 2024Query-Efficient Adversarial Attack Against Vertical Federated Graph Learningcited by 0