Federated Learning-Based Secure Data Analytics Framework for Smart Cities and IoT Applications
Keywords:
Federated Learning, Smart Cities, Internet of Things (IoT), Data Analytics, Edge Computing, Cybersecurity, Privacy Preservation, Machine Learning.Abstract
The growth of Internet of Things (IoT) devices and smart city infrastructures has led to the generation of large volumes of distributed data. Traditional centralized machine learning approaches require data to be collected and processed at cloud servers, which can create privacy concerns, increase communication costs, and introduce security risks. Federated Learning (FL) has emerged as an effective decentralized learning approach that enables collaborative model training while keeping data on local devices. This paper presents a Federated Learning-Based Secure Data Analytics Framework for smart city and IoT applications. The proposed framework combines secure aggregation, differential privacy, and edge computing techniques to improve data confidentiality, system scalability, and analytical performance. By enabling decentralized model training, the framework reduces the need for raw data sharing while maintaining high predictive accuracy. Experimental results demonstrate improvements in classification accuracy, communication efficiency, privacy protection, and computational performance when compared with conventional centralized machine learning methods. The proposed approach provides a secure, scalable, and efficient solution for intelligent data analytics in modern smart city and IoT environments.
References
1. Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., et al. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1–2), 1–210.
2. Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2022). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 39(3), 50–60.
3. Nguyen, D. C., Ding, M., Pathirana, P. N., et al. (2022). Federated learning for Internet of Things: A comprehensive survey. IEEE Communications Surveys & Tutorials, 24(3), 1622–1658.
4. Zhang, C., Xie, Y., Bai, L., Yu, B., Li, W., & Gao, Y. (2022). Privacy-preserving federated learning for IoT applications. Future Generation Computer Systems, 126, 95–106.
5. Mothukuri, V., Parizi, R. M., Pouriyeh, S., et al. (2022). A survey on security and privacy of federated learning. Future Generation Computer Systems, 115, 619–640.
6. Aledhari, M., Razzak, R., Parizi, R. M., & Saeed, F. (2022). Federated learning: A survey on enabling technologies and applications. IEEE Access, 10, 14026–14047.
7. Gajula, S. (2023). A Review of Anomaly Identification in Finance Frauds using Machine Learning System. International Journal of Current Engineering and Technology, 13(06).
8. Abreha, H. G., Hayajneh, M., & Serhani, M. A. (2023). Federated learning in smart cities: Concepts, applications, and challenges. Sensors, 23(4), 2105.
9. Sharma, P., Chen, J., & Park, J. H. (2023). Edge-assisted federated learning for smart city applications. Journal of Network and Computer Applications, 218, 103675.
10. Rahman, M. A., Islam, M. S., & Hassan, M. M. (2023). Secure federated learning framework for intelligent IoT systems. IEEE Internet of Things Journal, 10(12), 10523–10535.
11. Xu, J., Ghorbani, A. A., & Wang, Y. (2023). Differential privacy in federated learning: Recent advances and challenges. Information Sciences, 640, 119073.
12. Alazab, M., Gadekallu, T. R., & Reddy, M. P. K. (2024). Privacy-aware federated learning for secure smart city services. Computer Networks, 245, 110387.
13. Singh, S., Kumar, N., & Rodrigues, J. J. P. C. (2024). Federated edge intelligence for IoT-enabled smart environments. IEEE Transactions on Network Science and Engineering, 11(2), 1845–1858.
14. Wang, H., Liu, Y., & Chen, X. (2024). Secure aggregation techniques in federated learning: A review. ACM Computing Surveys, 57(1), 1–34.
15. Patel, K., Sharma, R., & Verma, A. (2025). Scalable federated learning architecture for smart city analytics. Future Internet, 17(1), 15–29.
16. Gupta, A., Mishra, D., & Kaur, P. (2025). Privacy-preserving machine learning for large-scale IoT networks using federated learning. IEEE Access, 13, 24561–24575.
17. Gajula, S. (2024). Cybersecurity risk prediction using graph neural networks. Journal of Information Systems Engineering and Management.
18. Chen, L., Zhao, Q., & Li, Y. (2025). Federated learning and edge computing integration for secure intelligent systems. Journal of Information Security and Applications, 82, 103912.
19. Rahman¹, M. A., Haque, B. T., Hossan, M. I., & Rubel⁴, M. S. K. C. (2024). Federated Threat Intelligence and Explainable Anomaly Detection for Distributed Network Environments in US Critical Infrastructure.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Bishop International Journal of Mathematics and Computer Science
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
