Differential Privacy and Federated Learning Technologies in Privacy Protection for Medical Big Data
Main Article Content
Keywords
big data, privacy protection, differential privacy, federated learning, medical data
Abstract
With the rapid development of big data technology, the value of data in various industries has become increasingly prominent, but the problem of privacy leakage has also received more and more attention. How to protect user privacy while mining the value of data has become an important problem that urgently needs to be solved in the field of big data analysis. This paper reviews and summarizes research related to privacy-preserving big data analysis from three levels: the algorithm level, the framework level, and the application level. First, the application and optimization methods of differential privacy (DP) in deep learning model training are introduced, including key technologies such as the differentially private stochastic gradient descent (DP-SGD) framework, gradient clipping, and privacy budget optimization. Then, the problem of improving model efficiency under the federated learning (FL) framework is discussed, with a focus on communication efficiency optimization and personalized FL methods under non-independent and identically distributed (non-IID) data. Finally, taking medical big data as a typical scenario, the research status and challenges of privacy protection systems are discussed. At the end of the paper, the existing problems in current research and future development directions are also preliminarily prospected.
References
- [1]Tan, Z., & Zhang, L. (2020). Survey on privacy-preserving machine learning. Journal of Software, 31(7), 2127-2156.
- [2]Liu, Y., Chen, H., Liu, Y., & Li, C. (2022). Privacy-preserving techniques in federated learning. Journal of Software, 33(3), 1057-1092.
- [3]Gu, Y., & Bai, Y. (2023). Research progress on model security and privacy of federated learning. Journal of Software, 34(6), 2833-2864.
- [4]Zhang, X., & Meng, X. (2014). Differential privacy in data publication and analysis. Chinese Journal of Computers, 37(4), 927-949.
- [5]Sha, H., Sun, L., Liu, Y., Xue, D., Wu, Y., Li, C., & Chen, H. (2026). Optimization of differentially private stochastic gradient descent: Methods, theories and applications. Chinese Journal of Computers, 49(6), 1307-1341.
- [6]Wang, K., Wang, Y., Liu, J., & Deng, J. (2025). Graph convolutional collaborative filtering recommendation algorithm based on Renyi differential privacy. Journal of Software, 36(3), 1202-1217.
- [7]Chen, S., Cai, J., & Sun, L. (2023). Differential privacy generative adversarial network algorithm with dynamic gradient threshold clipping. Journal of Computer Applications, 43(7), 2065-2072.
- [8]Zhou, Z., & Qian, X. (2022). A differential privacy protection algorithm for deep neural networks. Journal of Electronics and Information Technology, 44(5), 1773-1781.
- [9]Zhang, X., Zhang, L., & Zhang, Z. (2025). Federated learning method under user-level local differential privacy. Journal of Computer Research and Development, 62(2), 472-487.
- [10]Lu, Y., Jiang, Y., Feng, H., Guo, Z., & Xiang, S. (2025). Differential low-rank adaptation-based sensitive information protection for large language model training. Computer Engineering, 51(10), 1-14. https://doi.org/10.19678/j.issn.1000-3428.00252845.
- [11]Cao, S., Chen, C., Tang, P., & Su, S. (2023). Differentially private federated learning with functional mechanism. Chinese Journal of Computers, 46(10), 2178-2195.
- [12]Zhang, S., Zhang, J., Zhu, G., Long, S., & Li, Z. (2024). Personalized federated learning method based on Bregman divergence and differential privacy. Journal of Software, 35(11), 5249-5262. https://doi.org/10.13328/j.cnki.jos.007032.
- [13]Wang, T., Zhai, L., Yu, Y., Yang, T., Zhang, X., & Ren, X. (2025). Differentially private federated unlearning mechanism based on update residual. Scientia Sinica Informationis, 55(11), 2704-2721.
- [14]Yu, H., Fan, J., Sun, Y., Dong, H., & Xi, E. (2025). Survey of statistical heterogeneity in federated learning. Journal of Computer Applications, 45(9), 2737-2746.
- [15]Zheng, J., Liu, B., Lin, W., & Xie, J. (2025). Survey of communication efficiency for federated learning. Computer Science, 52(2), 1-7.
- [16]Liu, T., Yang, A., Weng, J., Chen, M., Liu, Y., & Zeng, H. (2026). Privacy-preserving heterogeneous federated learning participant selection based on secure multi-party computation. Journal of Software. Advance online publication. https://doi.org/10.13328/j.cnki.jos.007622.
- [17]Ping, F., & Fu, X. (2026). Personalized federated learning for concept and label distribution drift. Computer Science, 53(7), 433-441.
- [18]Jin, T., & Chen, S. (2023). Spectral clustering-based Fourier personalized federated learning. Journal of Electronics and Information Technology, 45(6), 1981-1989.
- [19]Liu, Y., Dai, Y., & Chen, G. (2025). Review of federated learning in medical image processing. Computer Science, 52(1), 183-193.
- [20]Zhang, M., Huang, J., & Han, L. (2021). Multi-keyword range search scheme for privacy protection of medical big data. Journal of Software, 32(10), 3266-3282.
- [21]Li, F., Li, H., Niu, B., & Qiu, W. (2022). Academic connotation and research trends of privacy computing. Chinese Journal of Network and Information Security, 8(6), 1-8.
- [22]Zhang, L., & Tan, Z. (2023). Federated learning privacy protection method for multimodal medical data. Computer Science, 50(S2), 933-940.
- [23]Wang, B., Li, H., Wang, J., & Guo, Y. (2023). Privacy-preserving federated learning architecture for medical data. Journal of Xidian University, 50(5), 166-177.
- [24]Nie, W., Xin, L., & Li, Z. (2022). Research on application of federated learning in medical informatization. Journal of Medical Informatics, 43(10), 12-16.
- [25]Li, R., Liu, T., Zheng, H., Chen, J., Liu, Z., & Ji, S. (2024). Privacy preservation method for vertical federated learning based on max-min strategy. Acta Automatica Sinica, 50(7), 1373-1388. https://doi.org/10.16383/j.aas.c211233.
- [26]Wang, J., & Kan, H. (2024). Fine-grained policy-hiding and traceable decentralized access control scheme in mHealth. Journal of Computer Research and Development, 61(6), 1525-1535.
- [27]Han, G., Wang, J., Luo, W., & Lu, Y. (2023). Research on medical data access control and secure sharing in public health events. Journal of Cyber Security, 8(1), 40-54.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.