Security and Resilience in Distributed ML by Kai Li (.ePUB)+
File Size: 50.4 MB
Security and Resilience in Distributed Machine Learning: Challenges, Techniques, and Future Directions by Kai Li, Xin Yuan, Wei Ni
Requirements: .ePUB, .PDF reader, 50.4 MB | True PDF, True EPUB
Overview: This book offers a comprehensive exploration of Federated Learning (FL), a novel approach to decentralized, privacy-preserving Machine Learning. This book delves into the resilience and security challenges inherent to FL, such as model poisoning and malicious attacks, that jeopardize system integrity. Through cutting-edge research and practical insights, the book introduces defense mechanisms like representational similarity analysis and visual explanation techniques, which safeguard FL models while ensuring performance and scalability. It also explores the evolving landscape of FL, including the integration of graph neural networks, Explainable AI, and energy-efficient designs that drive sustainability in distributed systems. As FL becomes increasingly vital across industries—from healthcare and finance to IoT and smart cities—this book addresses the critical balance between security, functionality, and compliance with global data privacy regulations. Guided by a vision of trustworthy and sustainable distributed intelligence, the book extends beyond threat modeling to explore the broader architectural design of resilient learning systems. It integrates graph neural networks, Explainable AI (XAI), energy-aware optimization, and privacy-preserving mechanisms to reconcile reliability, security, scalability, and regulatory compliance.
Genre: Non-Fiction > Tech & Devices
Free Download links: