Author: Dr. Priyanka Nair, Amit Bansal.
Abstract: Federated Learning (FL) is a decentralized machine learning paradigm that enables multiple clients to collaboratively train a shared model without exchanging raw data. This privacy-preserving approach addresses growing concerns about data security and regulatory compliance, particularly under frameworks such as GDPR and HIPAA. By transmitting only model updates, FL ensures that sensitive information remains local while still benefiting from collective intelligence. This paper examines the architecture, advantages, challenges, and real-world applications of federated learning, along with emerging strategies to enhance its security and efficiency.
Keywords: Federated Learning, Privacy-Preserving AI, Distributed Machine Learning, Data Security, Edge AI, GDPR Compliance, Secure Aggregation
Full Issue
| View or download the full issue | PDF 30-33 |