Federated Learning Systems Towards Privacy-Preserving Distributed AI

This book dives deep into both industry implementations and cutting-edge research driving the Federated Learning (FL) landscape forward. FL enables decentralized model training, preserves data privacy, and enhances security without relying on centralized datasets. Industry pioneers like NVIDIA have spearheaded the development of general-purpose FL platforms, revolutionizing how companies harness distributed data. Alternately, for medical AI, FL platforms, such as FedBioMed, enable collaborative model development across healthcare institutions to unlock massive value.
Research advances in PETs highlight ongoing efforts to ensure that FL is robust, secure, and scalable. Looking ahead, federated learning could transform public health by enabling global collaboration on disease prevention while safeguarding individual privacy. From recommendation systems to cybersecurity applications, FL is poised to reshape multiple domains, driving a future where collaboration and privacy coexist seamlessly.

Product details

• Assisted by: Muhammad Habib ur Rehman (Editor), Medhat Gaber (Editor), Muhammad Habib ur Rehman (Editor), Mohamed Medhat Gaber (Editor)
• Publisher: Springer, Berlin
• Content: Book
• Product form: Hardback
• Publication date: 12.02.2025
• Subject: Natural sciences, medicine, IT, technology > Technology > General, dictionaries
• EAN: 9783031788406
• ISBN: 978-3-0-3178840-6
• Pages: 165
• Illustrations: XVIII, 165 p. 30 illus., 25 illus. in color.
• Dimensions (packing): 15.5 x 1.3 x 23.5 cm
• Weight (packing): 391 g
• Series: Studies in Computational Intelligence
• Subjects: Systems, Applications, Algorithms, Artificial Intelligence, Healthcare, Security, Privacy, Computational Intelligence, recommender systems, Federated Learning, Intrusion Detection Systems, Client Selection