Privacy and security in federated learning systems: a review of methods and computational challenges
DOI:
https://doi.org/10.63862/rhs-v1n4-356-381-2026Keywords:
Federated learning, differential privacy, secure aggregation, cybersecurity, inference attacks, distributed machine learningAbstract
Federated learning enables model training on distributed information without necessarily centralizing raw records. Nevertheless, parameter exchanges, participant coordination, and malicious behavior create threats that do not disappear when data remain at their source. This paper examines privacy and security safeguards in federated learning systems and their computational trade-offs. A structured narrative literature review was conducted through a targeted search of verifiable academic sources and thematic analysis of foundational studies, methodological contributions, and surveys. Findings distinguish inference and reconstruction attacks, model poisoning, backdoors, and server-related threats, and compare differential privacy, secure aggregation, robust optimization, and verification mechanisms. The reviewed literature suggests that no single method simultaneously guarantees confidentiality, integrity, and availability. Appropriate protection depends on the threat model, architecture, accuracy requirements, communication overhead, and computational constraints. Trustworthy deployment, therefore, requires complementary safeguards, explicit evaluation metrics, and reproducible tests tailored to each use case.
Downloads
References
Chen, W.-N., Choo, C. A. C., Kairouz, P., & Suresh, A. T. (2022). The fundamental price of secure aggregation in differentially private federated learning. Proceedings of Machine Learning Research, 162, 3056–3089. https://proceedings.mlr.press/v162/chen22c.html
Chen, W.-N., Cormode, G., Bharadwaj, A., Romov, P., & Ozgur, A. (2024). Federated experiment design under distributed differential privacy. Proceedings of Machine Learning Research, 238, 2458–2466. https://proceedings.mlr.press/v238/chen24c.html
Girgis, A., Data, D., Diggavi, S., Kairouz, P., & Suresh, A. T. (2021). Shuffled model of differential privacy in federated learning. Proceedings of Machine Learning Research, 130, 2521–2529. https://proceedings.mlr.press/v130/girgis21a.html
Kairouz, P., McMahan, H. B., Avent, B., et al. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1–2), 1–210. https://doi.org/10.1561/2200000083
Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S., Stich, S., & Suresh, A. T. (2020). SCAFFOLD: Stochastic controlled averaging for federated learning. Proceedings of Machine Learning Research, 119, 5132–5143. https://proceedings.mlr.press/v119/karimireddy20a.html
Kerkouche, R., Ács, G., Castelluccia, C., & Genevès, P. (2021). Constrained differentially private federated learning for low-bandwidth devices. Proceedings of Machine Learning Research, 161, 1756–1765. https://proceedings.mlr.press/v161/kerkouche21a.html
Lowy, A., Ghafelebashi, A., & Razaviyayn, M. (2023). Private non-convex federated learning without a trusted server. Proceedings of Machine Learning Research, 206, 5749–5786. https://proceedings.mlr.press/v206/lowy23a.html
Ma, X., & Yan, M. (2024). Research progress on security and privacy of federated learning: A survey. Wireless Personal Communications, 136(4), 2201–2242. https://doi.org/10.1007/s11277-024-11372-0
Mangold, P., Durmus, A., Dieuleveut, A., & Moulines, E. (2025). Scaffold with stochastic gradients: New analysis with linear speed-up. Proceedings of Machine Learning Research, 267, 42902–42946. https://proceedings.mlr.press/v267/mangold25a.html
Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A. (2024). A survey of security strategies in federated learning: Defending models, data, and privacy. Future Internet, 16(10), Article 374. https://doi.org/10.3390/fi16100374
McMahan, B., Moore, E., Ramage, D., Hampson, S., & Agüera y Arcas, B. (2017). Communication-efficient learning of deep networks from decentralized data. Proceedings of Machine Learning Research, 54, 1273–1282. https://proceedings.mlr.press/v54/mcmahan17a.html
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021). A survey on security and privacy of federated learning. Future Generation Computer Systems, 115, 619–640. https://doi.org/10.1016/j.future.2020.10.007
Nguyen, J., Malik, K., Zhan, H., Yousefpour, A., Rabbat, M., Malek, M., & Huba, D. (2022). Federated learning with buffered asynchronous aggregation. Proceedings of Machine Learning Research, 151, 3581–3607. https://proceedings.mlr.press/v151/nguyen22b.html
Saha, S., Hota, A., Chattopadhyay, A. K., Nag, A., & Nandi, S. (2024). A multifaceted survey on privacy preservation of federated learning: Progress, challenges, and opportunities. Artificial Intelligence Review, 57, Article 184. https://doi.org/10.1007/s10462-024-10766-7
Zheng, Q., Chen, S., Long, Q., & Su, W. (2021). Federated f-differential privacy. Proceedings of Machine Learning Research, 130, 2251–2259. https://proceedings.mlr.press/v130/zheng21a.html
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Revista Hambatu Science

This work is licensed under a Creative Commons Attribution 4.0 International License.







