Conclusion
We have provided an enhanced privacy protection mechanism for FL. With the help of GAN, a local DP-FL framework has been proposed, and the privacy level, as well as the convergence performance, have been systemically conducted. Experimental results have shown the effectiveness and the advantages of the proposed algorithm by comparing it with the state of the art. In addition, further directions can find an optimal fake ratio and the number of training epochs for the proposed framework.
References
Abadi M, Chu A, Goodfellow I, et al. Deep learning with differential privacy. In: Proceedings of ACM SIGSAC Conference on Computer and Communications Security, 2016. 308–318
Wei K, Li J, Ding M, et al. Federated learning with differential privacy: algorithms and performance analysis. IEEE Trans Inform Forensic Secur, 2020, 15: 3454–3469
Webster R, Rabin J, Simon L, et al. Detecting overfitting of deep generative networks via latent recovery. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. 11273–11282
Shokri R, Stronati M, Song C Z, et al. Membership inference attacks against machine learning models. In: Proceedings of the IEEE Symposium on Security and Privacy, 2017. 3–18
Wei K, Li J, Ding M, et al. User-level privacy-preserving federated learning: analysis and performance optimization. IEEE Trans Mobile Comput, 2022, 21: 3388–3401
Acknowledgements
This work was supported in part by National Natural Science Foundation of China (Grant Nos. U22A2002, 61872184, 62002170, 62071234), Fundamental Research Funds for the Central Universities (Grant No. 30921013104), Future Network Grant of Provincial Education Board in Jiangsu, Zhejiang Lab (Grant No. 2022PD0AC02), Major Science and Technology Plan of Hainan Province (Grant No. ZDKJ2021022), and Scientific Research Fund Project of Hainan University (Grant No. KYQD(ZR)-21008).
Author information
Authors and Affiliations
Corresponding author
Additional information
Supporting information
Appendixes A–E. The supporting information is available online at info.scichina.com and link. springer.com. The supporting materials are published as submitted, without typesetting or editing. The responsibility for scientific accuracy and content remains entirely with the authors.
Rights and permissions
About this article
Cite this article
Li, J., Wei, K., Ma, C. et al. DP-GenFL: a local differentially private federated learning system through generative data. Sci. China Inf. Sci. 66, 189303 (2023). https://doi.org/10.1007/s11432-022-3678-7
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-022-3678-7