Privacy-Preserving Federated Learning Framework for Distributed Artificial Intelligence Systems
DOI:
https://doi.org/10.22399/ijcesen.5553Keywords:
Privacy-preserving federated learning, distributed artificial intelligence, TensorFlow Federated, secure aggregation, differential privacy, cloud computingAbstract
Privacy-preserving federated learning has become an important solution for secure distributed artificial intelligence systems. This study evaluates how federated learning protects sensitive data while maintaining model accuracy across distributed cloud environments. The research uses a secondary qualitative design, an inductive approach, and thematic analysis to examine published studies, industry reports, and cybersecurity datasets. The analysis focuses on TensorFlow Federated, Flower, OpenFL, and FedML frameworks and compares their privacy mechanisms, communication overhead, resource utilisation, and learning efficiency. The findings show that federated learning achieves high predictive performance while keeping raw data on local devices, reducing privacy risks during collaborative model training. The study also identifies communication overhead, heterogeneous client resources, and synchronisation delays as major challenges affecting distributed learning performance. Comparative cybersecurity findings indicate that stronger security maturity improves threat detection and privacy protection in federated environments. The study concludes that privacy-preserving federated learning offers a scalable and trustworthy framework for healthcare, finance, IoT, and cloud-native applications where data confidentiality is essential. It also recommends secure aggregation, differential privacy, adaptive client selection, and continuous cybersecurity monitoring to improve privacy, efficiency, and reliability in distributed artificial intelligence systems. The above research shows how privacy preserving federated learning contributes to the enhancement of artificial intelligence distributed computing. This framework offers an increase in the level of security of private information while offering good model accuracy. Privacy preserving federated learning decreases privacy leakage, enables secure collaboration on distributed devices, and enhances learning efficiency via decentralized learning.
References
1. Alshehri, F., & Muhammad, G. (2020). A comprehensive survey of the Internet of Things (IoT) and AI-based smart healthcare. IEEE access, 9, 3660-3678. https://ieeexplore.ieee.org/abstract/document/10066875/ DOI: https://doi.org/10.1109/ACCESS.2020.3047960
2. Bangad, N., Jayaram, V., Krishnappa, M. S., Banarse, A. R., Bidkar, D. M., Nagpal, A., & Parlapalli, V. (2024). A Theoretical Framework for AI-driven data quality monitoring in high-volume data environments. arXiv preprint arXiv:2410.08576. https://arxiv.org/abs/2410.08576
3. Burke, B., 2022. Artificial Intelligence & Machine Learning Report. https://pitchbook.com/news/reports/2021-annual-artificial-intelligence-machine-learning-report
4. Chong, S. W., & Reinders, H. (2020). Technology-mediated task-based language teaching: A qualitative research synthesis. Language Learning and Technology, 24(3), 70. https://pure.qub.ac.uk/en/publications/a-qualitative-research-synthesis/ DOI: https://doi.org/10.64152/10125/44739
5. Ghatge, S. K., & Parasar, A. (2023). Application of artificial intelligence (AI), internet of things (IoT), and big data in healthcare, finance, and transportation. PriMera Scientific Medicine and Public Health, 2(2023), 27-36. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4691289
6. Jiang, J., Kantarci, B., Oktug, S. F., & Soyata, T. (2020). Federated learning in smart city sensing: Challenges and opportunities. Sensors, 20(21), 6230. https://doi.org/10.3390/s20216230
7. Jiang, J., Kantarci, B., Oktug, S. F., & Soyata, T. (2020). Federated learning in smart city sensing: Challenges and opportunities. Sensors, 20(21), 6230. https://doi.org/10.3390/s20216230 DOI: https://doi.org/10.3390/s20216230
8. KPMG Cyber Security Annual Report, 2020. (CS)2AI-KPMG Control System Cyber Security Annual Report 2020. https://assets.kpmg.com/content/dam/kpmg/xx/pdf/2020/10/kpmg-control-system-cyber-security-annual-report.pdf
9. KPMG Cyber Security Annual Report, 2020. (CS)2AI-KPMG Control System Cyber Security Annual Report 2020. https://assets.kpmg.com/content/dam/kpmg/xx/pdf/2020/10/kpmg-control-system-cyber-security-annual-report.pdf
10. Li, Y., Zhou, Y., Jolfaei, A., Yu, D., Xu, G., & Zheng, X. (2020). Privacy-preserving federated learning framework based on chained secure multiparty computing. IEEE Internet of Things Journal, 8(8), 6178-6186. https://ieeexplore.ieee.org/document/9187932/ DOI: https://doi.org/10.1109/JIOT.2020.3022911
11. Liu, X., Yu, J., Liu, Y., Feng, Z., Ng, D. W. K., & Tsang, D. H. K. (2023). Distributed intelligence in wireless networks. IEEE Wireless Communications, 30(1), 54–61. https://doi.org/10.1109/MWC.005.2200301
12. Naeem, M., Ozuem, W., Howell, K., & Ranfagni, S. (2023). A step-by-step process of thematic analysis to develop a conceptual model in qualitative research. International journal of qualitative methods, 22, 16094069231205789. https://journals.sagepub.com/doi/abs/10.1177/16094069231205789 DOI: https://doi.org/10.1177/16094069231205789
13. Pasham, S. D. (2023). Privacy-preserving data sharing in big data analytics: A distributed computing approach. The Metascience, 1(1), 149-184. http://www.yuktabpublisher.com/index.php/TMS/article/view/130
14. Saeidi, M. A., Tabassum, H., & Alouini, M. S. (2023). Multi-band wireless networks: Architectures, challenges, and comparative analysis. IEEE Communications Magazine, 62(1), 80-86. https://ieeexplore.ieee.org/abstract/document/10179155/ DOI: https://doi.org/10.1109/MCOM.003.2300078
15. Schneider, A., Wagenknecht, A., Sydow, H., Riedlinger, D., Holzinger, F., Figura, A., ... & Möckel, M. (2023). Primary and secondary data in emergency medicine health services research–a comparative analysis in a regional research network on multimorbid patients. BMC Medical Research Methodology, 23(1), 34. https://link.springer.com/article/10.1186/s12874-023-01855-2 DOI: https://doi.org/10.1186/s12874-023-01855-2
16. Sibeoni, J., Verneuil, L., Manolios, E., & Révah-Levy, A. (2020). A specific method for qualitative medical research: the IPSE (Inductive Process to analyze the Structure of lived Experience) approach. BMC Medical Research Methodology, 20(1), 216. https://link.springer.com/article/10.1186/s43058-021-00202-0 DOI: https://doi.org/10.1186/s12874-020-01099-4
17. Singh, R., Dwivedi, A. D., Srivastava, G., Chatterjee, P., & Lin, J. C. W. (2023). A privacy-preserving internet of things smart healthcare financial system. IEEE Internet of Things Journal, 10(21), 18452-18460. https://ieeexplore.ieee.org/document/10004952/ DOI: https://doi.org/10.1109/JIOT.2022.3233783
18. Stanford Institute for Human-Centered Artificial Intelligence. (2021). Artificial Intelligence Index Report 2021. https://hai.stanford.edu/assets/files/2021-ai-index-report_master.pdf
19. Sun, T., Li, D., & Wang, B. (2022). Decentralized federated averaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4289-4301. https://ieeexplore.ieee.org/abstract/document/9850408/ DOI: https://doi.org/10.1109/TPAMI.2022.3196503
20. Taherdoost, H. (2021). Data collection methods and tools for research; a step-by-step guide to choose data collection technique for academic and business research projects. International journal of academic research in management (IJARM), 10(1), 10-38. https://hal.science/Hal-03741847/
21. Xia, Y., Yang, D., Li, W., Myronenko, A., Xu, D., Obinata, H., ... & Roth, H. (2021). Auto-fedavg: learnable federated averaging for multi-institutional medical image segmentation. arXiv preprint arXiv:2104.10195. https://arxiv.org/abs/2104.10195
22. Zhou, Y., Ye, Q., & Lv, J. (2021). Communication-efficient federated learning with compensated overlap-fedavg. IEEE Transactions on Parallel and Distributed Systems, 33(1), 192-205. https://ieeexplore.ieee.org/abstract/document/9459540/ DOI: https://doi.org/10.1109/TPDS.2021.3090331
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
