Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

GraphPub: Generation of Differential Privacy Graph with High Availability (2403.00030v2)

Published 28 Feb 2024 in cs.SI, cs.AI, cs.CR, and cs.LG

Abstract: In recent years, with the rapid development of graph neural networks (GNN), more and more graph datasets have been published for GNN tasks. However, when an upstream data owner publishes graph data, there are often many privacy concerns, because many real-world graph data contain sensitive information like person's friend list. Differential privacy (DP) is a common method to protect privacy, but due to the complex topological structure of graph data, applying DP on graphs often affects the message passing and aggregation of GNN models, leading to a decrease in model accuracy. In this paper, we propose a novel graph edge protection framework, graph publisher (GraphPub), which can protect graph topology while ensuring that the availability of data is basically unchanged. Through reverse learning and the encoder-decoder mechanism, we search for some false edges that do not have a large negative impact on the aggregation of node features, and use them to replace some real edges. The modified graph will be published, which is difficult to distinguish between real and false data. Sufficient experiments prove that our framework achieves model accuracy close to the original graph with an extremely low privacy budget.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (26)
  1. The political blogosphere and the 2004 us election: divided they blog. In Proceedings of the 3rd international workshop on Link discovery, pages 36–43, 2005.
  2. Explainable gnn-based models over knowledge graphs. In International Conference on Learning Representations, 2021.
  3. Graph neural networks for modelling traffic participant interaction. In 2019 IEEE Intelligent Vehicles Symposium (IV), pages 695–701. IEEE, 2019.
  4. Cynthia Dwork. Differential privacy: A survey of results. In International conference on theory and applications of models of computation, pages 1–19. Springer, 2008.
  5. Inductive representation learning on large graphs. Advances in neural information processing systems, 30, 2017.
  6. Large-scale privacy-preserving network embedding against private link inference attacks. arXiv preprint arXiv:2205.14440, 2022.
  7. Degree-preserving randomized response for graph neural networks under local differential privacy. arXiv preprint arXiv:2202.10209, 2022.
  8. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33:22118–22133, 2020.
  9. Privacy-preserving graph convolutional networks for text classification. arXiv preprint arXiv:2102.09604, 2021.
  10. Edge-level privacy in graph neural networks. In 18th International Workshop on Mining and Learning with Graphs, 2022.
  11. Towards private learning on decentralized graphs with local differential privacy. arXiv preprint arXiv:2201.09398, 2022.
  12. Sok: Differential privacy on graph-structured data. arXiv preprint arXiv:2203.09205, 2022.
  13. Reverse graph learning for graph neural network. IEEE Transactions on Neural Networks and Learning Systems, 2022.
  14. A privacy-preserving subgraph-level federated graph neural network via differential privacy. arXiv preprint arXiv:2206.03492, 2022.
  15. Graph attention auto-encoders. arXiv preprint arXiv:1905.10715, 2019.
  16. Collective classification in network data. AI magazine, 29(3):93–93, 2008.
  17. The anatomy of the facebook social graph. arXiv preprint arXiv:1111.4503, 2011.
  18. Graph attention networks. stat, 1050:20, 2017.
  19. A review on graph neural network methods in financial applications. arXiv preprint arXiv:2111.15367, 2021.
  20. Semi-supervised classification with graph convolutional networks. In J. International Conference on Learning Representations (ICLR 2017), 2016.
  21. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1):4–24, 2020.
  22. Deep learning on graphs for natural language processing. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2651–2653, 2021.
  23. Linkteller: Recovering private edges from graph neural networks via influence analysis. In 2022 IEEE Symposium on Security and Privacy (SP), pages 2005–2024. IEEE, 2022.
  24. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, 32, 2019.
  25. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  26. Graphmi: Extracting private graph data from graph neural networks. arXiv preprint arXiv:2106.02820, 2021.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now