V.J.K. Kishor Sonti¹*, Sai Varun C², Sivasangari A³ and A Ronald Doni³

¹Professor, Department of ECE, Sathyabama Institute of Science and Technology, India
²Student, Department of CSE, Sathyabama Institute of Science and Technology, India
³Professor, Department of CSE, Sathyabama Institute of Science and Technology, India

*Corresponding Author:V.J.K. Kishor Sonti, Professor, Department of ECE, Sathyabama Institute of Science and Technology, India.

Received: September 23, 2025; Published: October 17, 2025

Abstract

In today’s world, privacy and security are the most important challenges to be addressed. The increasing number of interconnected devices has led to more data generation, creating many opportunities as well as vulnerabilities for Machine Learning (ML) applications. Decentralized Artificial Intelligent (AI) systems like Federated Learning (FL) have addressed all the issues related to data privacy and security. This is being achieved by introducing a secure distributed ML process, where there would be multiple nodes or local models and one global model or the server. This approach allows for multiple nodes to be trained individually on the training data and share a global model. This is trained by aggregating the weights obtained from all the nodes. A detailed view about the fundamentals of FL is presented in this work. The fundamentals of FL are explored with working principles, advantages and challenges faced with FL. Various case studies are provided about the usage of FL by various organizations to ensure data privacy and security. A detailed explanation about impact of FL and applications is presented. This also narrates the problems addressed, classifications of FL, challenges and its applications in various sectors. Additionally, the performance evaluation of FL is provided and is compared with the traditional AI systems by measuring accuracy, execution time, convergence time and Central Processing Unit (CPU) usage. This highlights the use of FL for ensuring privacy and security without affecting the performance of the AI model. The future scope section provides a comprehensive idea of further expansion of this concept of FL. This would be a comprehensive guide for academicians, researchers and enterprises as it offers an approach for ensuring data privacy and security without affecting the performance of the model. Various enterprises are struggling with privacy concerns, this chapter can guide them to employ this proposed approach to prevent any risk or data breach. This approach also ensure the safety of confidentiality data such as consumer data, employee data and all.

Keywords: Federated Learning; Case Studies; Confidentiality; Data; Privacy

References

1. Gong M., et al. “Privacy-enhanced multi-party deep learning”. Neural Networks 121 (2020): 484-496.
2. Xie Y., et al. “Secure collaborative few-shot learning”. Knowledge-Based Systems 203 (2020): 106157.
3. Bonawitz K. “Towards federated learning at scale: System design”. arXiv preprint arXiv (2019): 1902.01046.
4. Zhang C., et al. “A privacy-preserving multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition”. Frontiers in Neurorobotics 13 (2020): 112.
5. Albrecht JP. “How the GDPR will change the world”. European Data Protection Law Review: EDPL 2 (2016): 287.
6. Regulation P. “Regulation (EU) 2016/679 of the European Parliament and of the Council”. Regulation (eu) (2016): 679.
7. Boban M. “Digital single market and EU data protection reform with regard to the processing of personal data as the challenge of the modern world”. Economic and Social Development: Book of Proceedings (2016): 191.
8. Yazici İ., et al. “A survey of applications of artificial intelligence and machine learning in future mobile networks-enabled systems”. Engineering Science and Technology, an International Journal 44 (2023): 101455.
9. Konečný J., et al. “Federated optimization: Distributed machine learning for on-device intelligence”. arXiv preprint arXiv (2016): 1610.02527.
10. Kairouz P., et al. “Advances and open problems in federated learning”. Foundations and Trends® in Machine Learning1–2 (2021): 1-210.
11. Shokri R and Shmatikov V. “Privacy-preserving deep learning”. In Proceedings of the 22nd ACM SIGSAC conference on computer and communications security (2015): 1310-1321.
12. Yurdem B., et al. “Federated learning: Overview, strategies, applications, tools and future directions”. Heliyon (2024).
13. Gong M., et al. “A survey on differentially private machine learning”. IEEE Computational Intelligence Magazine2 (2020): 49-64.
14. Zhang C., et al. “A survey on federated learning”. Knowledge-Based Systems 216 (2021): 106775.
15. Li T., et al. “Federated learning: Challenges, methods, and future directions”. IEEE Signal Processing Magazine3 (2020): 50-60.
16. Xu J., et al. “Federated learning for healthcare informatics”. Journal of Healthcare Informatics Research 5 (2021): 1-19.
17. McMahan B., et al. “Communication-efficient learning of deep networks from decentralized data”. In Artificial intelligence and statistics (2017): 1273-1282.
18. Flanagan A., et al. “Federated multi-view matrix factorization for personalized recommendations”. In Machine learning and knowledge discovery in databases: European conference, ECML PKDD 2020, Ghent, Belgium, September 14–18, 2020, Proceedings, Part II (2021): 324-347.
19. Li T., et al. “Fair resource allocation in federated learning”. arXiv preprint arXiv (2019): 1905.10497.
20. Blanco-Justicia A., et al. “Achieving security and privacy in federated learning systems: Survey, research challenges and future directions”. Engineering Applications of Artificial Intelligence 106 (2021): 104468.
21. Kairouz P., et al. “Advances and open problems in federated learning”. Foundations and Trends® In Machine Learning 1–2 (2021): 1-210.
22. Liu Y., et al. “A secure federated transfer learning framework”. IEEE Intelligent Systems4 (2020): 70-82.
23. Bonawitz K., et al. “Practical secure aggregation for privacy-preserving machine learning”. In proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (2017): 1175-1191.

Citation

Citation: V.J.K. Kishor Sonti., et al. “Federated Learning - An Emerging Scenario of Future Data Science" Acta Scientific Computer Sciences 7.8 (2025): 14-19.

Copyright

Copyright: © 2025 V.J.K. Kishor Sonti., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.