A Privacy-Preserving Data Sharing Framework Based on Generative Adversarial Networks
Keywords:
privacy-preserving data sharing, generative adversarial networks, differential privacy, multi-discriminator mechanism, controllable generationAbstract
This paper proposes a privacy-preserving data sharing framework based on Generative Adversarial Networks (GANs), integrating a multi-discriminator mechanism, a dynamic differential privacy adjustment strategy, and a controllable generation module. The framework aims to balance data utility and privacy protection across high-risk domains. In medical data sharing (MIMIC-III) and cross-institutional financial analysis, experiments show that the proposed approach outperforms standard GANs, Differential Privacy Logistic Regression, and Federated Learning in generation quality, downstream task performance, and resistance to inference attacks. The multi-discriminator design constrains the generator from statistical, semantic, and temporal perspectives to mitigate mode collapse, while the dynamic privacy strategy adapts noise levels during training to optimize the privacy-utility trade-off. The controllable generation module enables tailored data distributions for specific business needs, improving minority-class performance. Although the framework introduces computational overhead, it offers a viable solution for secure, high-quality data sharing. Future work will focus on lightweight architectures, automated parameter tuning, and multimodal, cross-domain extensions to enhance adaptability and scalability.References
1. A. Wijesinghe, S. Zhang, and Z. Ding, "Ps-fedgan: an efficient federated learning framework based on partially shared generative adversarial networks for data privacy," arXiv preprint arXiv:2305.11437, 2023.
2. T. T. Khoei, and A. Singh, "Data reduction in big data: a survey of methods, challenges and future directions," International Journal of Data Science and Analytics, vol. 20, no. 3, pp. 1643-1682, 2025. doi: 10.1007/s41060-024-00603-z
3. O. Ngwenyama, F. Rowe, S. Klein, and H. Z. Henriksen, "The open prison of the big data revolution: false consciousness, faustian bargains, and digital entrapment," Information Systems Research, vol. 35, no. 4, pp. 2030-2058, 2024. doi: 10.1287/isre.2020.0588
4. Z. Wang, Z. Liu, C. Fu, A. Wen, M. Zhang, and W. Zhang, "Privacy-preserving multiparty power data sharing based on generative adversarial network," In Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023), May, 2024, pp. 2601-2608.
5. A. Baseera, J. M. Scaria, A. Trivedi, M. Sharma, P. Sharma, and P. Saini, "Advanced Techniques for Protecting Privacy in Artificial Intelligence Powered Medical Systems," In 2024 IEEE 4th International Conference on ICT in Business Industry & Government (ICTBIG), December, 2024, pp. 1-9.
6. W. Zhang, H. Liu, B. Li, J. Xie, Y. Huang, Y. Li, and B. Ghanem, "Dynamically masked discriminator for GANs," Advances in Neural Information Processing Systems, vol. 36, pp. 23094-23114, 2023.
7. S. Sangeetha, E. Shriaarthy, N. Rithvik Pranao, J. S. Priya, L. Yogeswari, S. Gokul, and S. S. Nandha, "Elevating Privacy: A Differential Privacy Infused Approach to GAN for Robust Data Synthesis for Deep Learning Models," In Advanced Computing and Communications Conference, December, 2024, pp. 267-278.
8. P. Purwono, A. N. E. Wulandari, A. Ma'arif, and W. A. Salah, "Understanding Generative Adversarial Networks (GANs): A Review," Control Systems and Optimization Letters, vol. 3, no. 1, pp. 36-45, 2025. doi: 10.59247/csol.v3i1.170
9. A. Dash, J. Ye, and G. Wang, "A review of generative adversarial networks (GANs) and its applications in a wide variety of disciplines: from medical to remote sensing," IEEE Access, vol. 12, pp. 18330-18357, 2023. doi: 10.1109/access.2023.3346273
10. Z. Sun, H. Zhang, J. Bai, M. Liu, and Z. Hu, "A discriminatively deep fusion approach with improved conditional GAN (im-cGAN) for facial expression recognition," Pattern Recognition, vol. 135, p. 109157, 2023. doi: 10.1016/j.patcog.2022.109157
11. Y. Wang, S. Xiao, and P. Ye, "SAGAN: Self-attention Generative Adversarial Network for RGB-D Saliency Prediction," In International Conference on Image and Graphics, September, 2023, pp. 115-123. doi: 10.1007/978-3-031-46308-2_10
12. T. Hasegawa, and K. Fujino, "Adversarial Perturbation for Sensor Data Anonymization: Balancing Privacy and Utility," Computers, Materials & Continua, vol. 84, no. 2, 2025. doi: 10.32604/cmc.2025.066270
13. Y. Li, Y. Wang, Q. Fan, Z. Pan, Y. Wu, Z. Zhang, and W. Zhou, "Secure Multi-party Learning: Fundamentals, Frameworks, State of the Art, Trends, and Challenges," IEEE Transactions on Network Science and Engineering, 2025. doi: 10.1109/tnse.2025.3566140
14. A. Yao, G. Li, X. Li, F. Jiang, J. Xu, and X. Liu, "Differential privacy in edge computing-based smart city Applications: Security issues, solutions and future directions," Array, vol. 19, p. 100293, 2023.
