mlsanityData to 7 Oct 2026

Releasing Graph Neural Networks with Differential Privacy Guarantees

arXiv 2109.08907 ↗First posted 18 Sep 2021cs.LG cs.CRcited by 32

Not on the map. Why?

Abstract (arXiv)

With the increasing popularity of graph neural networks (GNNs) in several sensitive applications like healthcare and medicine, concerns have been raised over the privacy aspects of trained GNNs. More notably, GNNs are vulnerable to privacy attacks, such as membership inference attacks, even if only black-box access to the trained model is granted. We propose PrivGNN, a privacy-preserving framework for releasing GNN models in a centralized setting. Assuming an access to a public unlabeled graph, PrivGNN provides a framework to release GNN models trained explicitly on public data along with knowledge obtained from the private data in a privacy preserving manner. PrivGNN combines the knowledge-distillation framework with the two noise mechanisms, random subsampling, and noisy labeling, to ensure rigorous privacy guarantees. We theoretically analyze our approach in the Renyi differential privacy framework. Besides, we show the solid experimental performance of our method compared to several baselines adapted for graph-structured data. Our code is available at https://github.com/iyempissy/privGnn.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 31 of its 52 references that are in the map. First posted on arXiv 18 Sep 2021.

Builds on

31 of 52 references.

References · 31

  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. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  8. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  9. 2019Graph Neural Networks for Social Recommendationcited by 711
  10. 2015Image-based Recommendations on Styles and Substitutescited by 702
  11. 2017Renyi Differential Privacycited by 643
  12. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
19 more
  1. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  2. 2018Scalable Private Learning with PATEcited by 266
  3. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
  4. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 234
  5. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  6. 2020Quantifying Privacy Leakage in Graph Embeddingcited by 82
  7. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  8. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  9. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  10. 2020Locally Private Graph Neural Networkscited by 64
  11. 2020Vertically Federated Graph Neural Network for Privacy-Preserving Node Classificationcited by 61
  12. 2021Graph Embedding for Recommendation against Attribute Inference Attackscited by 40
  13. 2020ORCAS: 18 Million Clicked Query-Document Pairs for Analyzing Searchcited by 34
  14. 2021DGCN: Diversified Recommendation with Graph Convolutional Networkscited by 29
  15. 2018Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistrycited by 25
  16. 2019Privacy-Aware Recommendation with Private-Attribute Protection using Adversarial Learningcited by 21
  17. 2021Privacy-Preserving Graph Convolutional Networks for Text Classificationcited by 19
  18. 2021Towards Representation Identical Privacy-Preserving Graph Neural Network via Split Learningcited by 10
  19. 2020Encounters with Visual Misinformation and Labels Across Platforms: An Interview and Diary Study to Inform Ecosystem Approaches to Misinformation Interventionscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 9; 2024: 4; 2025: 6; 2026: 3.

32 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  2. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  3. 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
  4. 2022Certified Graph Unlearningcited by 46
  5. 2021Node-Level Differentially Private Graph Neural Networkscited by 43
  6. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  7. 2022Private Graph Extraction via Feature Explanationscited by 16
  8. 2023ProGAP: Progressive Graph Neural Networks with Differential Privacy Guaranteescited by 12
  9. 2023Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protectioncited by 12
  10. 2023A Survey of Graph Unlearningcited by 12
  11. 2023Preserving Node-level Privacy in Graph Neural Networkscited by 11
  12. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
20 more
  1. 2022SoK: Differential Privacy on Graph-Structured Datacited by 9
  2. 2022Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacycited by 7
  3. 2023Does Black-box Attribute Inference Attacks on Graph Neural Networks Constitute Privacy Risk?cited by 7
  4. 2022Graph Generative Model for Benchmarking Graph Neural Networkscited by 6
  5. 2023Local Differential Privacy in Graph Neural Networks: a Reconstruction Approachcited by 5
  6. 2022Privacy and Transparency in Graph Machine Learning: A Unified Perspectivecited by 4
  7. 2025Safeguarding Graph Neural Networks against Topology Inference Attackscited by 3
  8. 2022Privacy-Preserved Neural Graph Similarity Learningcited by 2
  9. 2023Privacy-preserving design of graph neural networks with applications to vertical federated learningcited by 2
  10. 2025Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defensescited by 2
  11. 2024Privately Learning from Graphs with Applications in Fine-tuning Large Language Modelscited by 1
  12. 2025AdvSGM: Differentially Private Graph Learning via Adversarial Skip-gram Modelcited by 1
  13. 2026Impact of Graph Structure on Membership-Inference Risk for Graph Neural Networkscited by 1
  14. 2023Differentially Private Graph Neural Network with Importance-Grained Noise Adaptioncited by 0
  15. 2024Vision Paper: Designing Graph Neural Networks in Compliance with the European Artificial Intelligence Actcited by 0
  16. 2025Structure-Preference Enabled Graph Embedding Generation under Differential Privacycited by 0
  17. 2025DP-GPL: Differentially Private Graph Prompt Learningcited by 0
  18. 2025Differentially Private Relational Learning with Entity-level Privacy Guaranteescited by 0
  19. 2026Adversarial Attacks on Locally Private Graph Neural Networkscited by 0
  20. 2026Bayesian Membership Privacy for Graph Neural Networkscited by 0