FEDERATED LEARNING: ENHANCING PRIVACY IN AI SYSTEMS

Authors

  • Dr. Ayesha Khan Department of Computer Science, National University of Science and Technology (NUST), Islamabad, Pakistan.

DOI:

https://doi.org/10.71465/csb9

Keywords:

Federated Learning, Privacy-Preserving AI, Distributed Learning, Data Security, Decentralized AI Systems

Abstract

Federated Learning (FL) has emerged as a transformative paradigm in artificial intelligence (AI) by enabling distributed model training while preserving data privacy. Unlike traditional centralized approaches, FL allows data to remain on local devices, mitigating privacy risks and complying with stringent data protection regulations. This study explores the principles of FL, its applications in various domains, privacy-preserving techniques, and challenges in implementation. The findings highlight the potential of FL in fostering collaboration among decentralized data sources without compromising user privacy. Recommendations for future research focus on improving model performance, security, and scalability.

image

Downloads

Published

2018-06-30