Federated Learning: A Privacy Preserving Approach for Decentralized Machine Learning
International Journal of Innovative Science and Research Technology · 13.03.2026 · 580
DOI: 10.38124/ijisrt/26mar171 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 13.03.2026. Verfasst von Arya K. S. und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.
Abstract (Originalsprache)
Federated Learning (FL) allows decentralized model training while maintaining data locality, yet remains vulnerable to gradient-based leakage. This paper examines core FL algorithms and integrates privacy-preserving techniques, specifically Differential Privacy, Homomorphic Encryption, and Secure Aggregation. We analyze the performance trade-offs between security and computational efficiency, establishing a framework for secure collaborative AI.
Zitieren
APA
S., A. K., & A., A. (2026). Federated Learning: A Privacy Preserving Approach for Decentralized Machine Learning. International Journal of Innovative Science and Research Technology, 580. https://doi.org/10.38124/ijisrt/26mar171
Vancouver
S. AK, A. A. Federated Learning: A Privacy Preserving Approach for Decentralized Machine Learning. International Journal of Innovative Science and Research Technology. 2026:580. doi:10.38124/ijisrt/26mar171
BibTeX
@article{S2026,
author = {S., Arya K. and A., Aparna},
title = {Federated Learning: A Privacy Preserving Approach for Decentralized Machine Learning},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {580},
doi = {10.38124/ijisrt/26mar171}
}
EUVIMED