Federated Learning for Privacy Preserving Artificial Intelligence: A Survey and Technical Analysis
International Journal of Advanced Research in Science Communication and Technology · 30.04.2026 · 441
DOI: 10.48175/ijarsct-34457 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 30.04.2026. Verfasst von Snehal Bagal und 3 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben.
Abstract (Originalsprache)
The accelerated use of artificial intelligence in many applications has led to an increased need for huge amounts of data to be used in machine learning tasks. Classical machine learning solutions usually involve centralization of the process through which data from several different sources is collected at one server location and then fed into the learning model. Such a practice causes numerous problems related to data privacy, possible security threats, and compliance with any relevant regulations due to the sensitive nature of the information collected. One solution to the above mentioned issues has been developed as federated learning – the machine learning method in which a number of participants can collaborate in order to improve the learning results by training the global model while keeping their data safe at their locations. The federated learning approach involves a participant performing learning tasks with their individual dataset before sharing updates with a coordinating server.
Zitieren
APA
Bagal, S., Salian, Y., Sayyad, S., & Somkuwar, A. (2026). Federated Learning for Privacy Preserving Artificial Intelligence: A Survey and Technical Analysis. International Journal of Advanced Research in Science Communication and Technology, 441. https://doi.org/10.48175/ijarsct-34457
Vancouver
Bagal S, Salian Y, Sayyad S, Somkuwar A. Federated Learning for Privacy Preserving Artificial Intelligence: A Survey and Technical Analysis. International Journal of Advanced Research in Science Communication and Technology. 2026:441. doi:10.48175/ijarsct-34457
BibTeX
@article{Bagal2026,
author = {Bagal, Snehal and Salian, Yashas and Sayyad, Sohail and Somkuwar, Amulya},
title = {Federated Learning for Privacy Preserving Artificial Intelligence: A Survey and Technical Analysis},
journal = {International Journal of Advanced Research in Science Communication and Technology},
year = {2026},
pages = {441},
doi = {10.48175/ijarsct-34457}
}
EUVIMED