Federated Learning for Privacy-Preserving AI: Innovations in Healthcare and Personal Data Analytics

EasyChair Preprint 15380

Abstract

With the rise of AI-driven data analytics in healthcare and personal data sectors, privacy preservation has become a critical concern. Federated learning (FL), a decentralized machine learning approach, has emerged as a promising solution by allowing data to be processed locally while sharing only model updates to maintain privacy. This paper explores the role of FL in advancing privacy-preserving AI for healthcare and personal data analytics, addressing key areas such as data security, model accuracy, and regulatory compliance. Analyzing recent FL advancements, this study examines the practical applications and limitations of FL in real-world healthcare environments, providing insights into the future of privacy-aware AI.

Keyphrases: Data Security, Decentralized Machine Learning, Federated Learning, Healthcare data, Personal Data Analytics, Privacy-Preserving AI, Regulatory Compliance, model accuracy

@booklet{EasyChair:15380,
  author    = {Ava Nakamura},
  title     = {Federated Learning for Privacy-Preserving AI: Innovations in Healthcare and Personal Data Analytics},
  howpublished = {EasyChair Preprint 15380},
  year      = {EasyChair, 2024}}