Abstract

Federated Learning (FL) has emerged as a transformative approach to decentralized machine learning, enabling model training across multiple devices without centralizing sensitive data. While FL inherently supports privacy, growing concerns around data security, regulatory compliance, and ethical accountability have led to the development of advanced privacy preserving mechanisms. This systematic review, conducted in adherence with PRISMA guidelines, explores the landscape of privacy enhancing techniques, legal regulations, and ethical implications associated with Federated Learning. We sourced peer reviewed literature from 2016 to 2024 across major scientific databases, including IEEE Xplore, SpringerLink, and ACM Digital Library. The review identifies and categorizes approaches such as Differential Privacy, Homomorphic Encryption, and Secure Multi party Computation. We further evaluate the alignment of FL practices with legal standards such as GDPR, HIPAA, and CCPA, and highlight ethical considerations including fairness, transparency, and user consent. Our analysis reveals critical gaps in interdisciplinary integration, particularly the need for frameworks that simultaneously meet technical robustness, legal compliance, and ethical accountability. We propose directions for future research, emphasizing a holistic approach that incorporates multi stakeholder engagement to realize trustworthy and scalable FL systems.