Handbook of Trustworthy Federated Learning

Herausgegeben:Thai, My T.; Phan, Hai N.; Thuraisingham, Bhavani

• Gebundenes Buch

Produktbeschreibung

This handbook aims to serve as a one-stop, reliable resource, including curated surveys and expository contributions on federated learning. It covers a comprehensive range of topics, providing the reader with technical and non-technical fundamentals, applications, and extensive details of various topics. The readership spans from researchers and academics to practitioners who are deeply engaged or are starting to venture into the realms of trustworthy federated learning. First introduced in 2016, federated learning allows devices to collaboratively learn a shared model while keeping raw data localized, thus promising to protect data privacy. Since its introduction, federated learning has undergone several evolutions. Most importantly, its evolution is in response to the growing recognition that its promise of collaborative learning is inseparable from the imperatives of privacy preservation and model security.

The resource is divided into four parts. Part 1 (Security and Privacy) explores the robust defense mechanisms against targeted attacks and addresses fairness concerns, providing a multifaceted foundation for securing Federated Learning systems against evolving threats. Part 2 (Bilevel Optimization) unravels the intricacies of optimizing performance in federated settings. Part 3 (Graph and Large Language Models) addresses the challenges in training Graph Neural Networks and ensuring privacy in Federated Learning of natural language models. Part 4 (Edge Intelligence and Applications) demonstrates how Federated Learning can empower mobile applications and preserve privacy with synthetic data.

Produktdetails

• Springer Optimization and Its Applications 213
• Verlag: Springer / Springer International Publishing / Springer, Berlin
• Artikelnr. des Verlages: 978-3-031-58922-5
• 2025
• Seitenzahl: 440
• Erscheinungstermin: 4. September 2024
• Englisch
• Abmessung: 241mm x 160mm x 30mm
• Gewicht: 766g
• ISBN-13: 9783031589225
• ISBN-10: 303158922X
• Artikelnr.: 70209594

Autorenporträt

My T. Thai is a Research Foundation Professor of Computer & Information Sciences & Engineering and Associate Director of UF Nelms Institute for the Connected World at the University of Florida, USA. Dr. Thai has extensive expertise in Trustworthy AI, Security and Privacy, Network Science, and Optimization. She has published 7 books and over 300+ papers in leading academic journals and conferences with severable best papers awards from the IEEE, ACM, and AAAI. The two latest ones are AAAI 2023 Distinguished Papers Award and 2023 ACM Web Science Trust Test-of-Time Award. Dr. Thai is the recipient of various awards, including DTRA Young Investigator Award and NSF CAREER Award. In addition, Dr. Thai is TPC-chairs and general chairs of many IEEE international conferences and on the editorial board of several journals. She is currently the Editor-in-Chief of the Journal of Combinatorial Optimization (JOCO), the IET Blockchain journal, and a book series editor of Springer Optimization and its Application. Dr. Thai is a Fellow of IEEE.   Hai N. Phan is an Associate Professor at the NJIT. Dr. Phan's topic of interest mainly concerns privacy and security, machine learning, health informatics, social network analysis, and spatiotemporal data mining. Dr. Phan received his Ph.D. in Computer Science from the University of Montpellier 2 in October 2013. Dr. Phan has established a strong expertise in the field, i.e., privacy and security, ML, and health informatics, with over 47 publications. Many of them were published at leading venues, including ICML, ECML, AAAI, IJCAI, ACM SigSpatial, ACM Multimedia, etc., with several best papers, i.e., IEEE ICDM'17, Springer CSoNet'19, Springer CSoNet'18, ACM in preserving scalable DP and LDP in deep learning, such as auto-encoders, CNNs, continual and adversarial learning, network embedding, language modeling, certified robustness against model attacks, representation learning, and FL.   Bhavani Thuraisingham is the Founders Chair Professor of Computer Science and the Executive Director of the Cyber Security Research and Education Institute at the University of Texas at Dallas. Dr. Thuraisingham has 35+ years of work experiences in the commercial industry (Honeywell), Federally Funded Research and Development Center (MITRE), Government (NSF) and Academia. She has conducted research in cyber security for thirty years and specializes in applying data analytics for cyber security. Her work has resulted in over 100 keynote addresses, 120 journal papers, 300 conference papers, 15 books, and 8 patents. She is a Fellow of ACM, IEEE, AAAS, NAI, and IMA.

Inhaltsangabe

.- Trustworthiness, Privacy and Security in Federated Learning. - Secure Federated Learning.- Data Poisoning and Leakage Analysis in Federated Learning.- Robust Federated Learning against Targeted Attackers using Model Updates Correlation.- Un-Fair Trojan: Targeted Backdoor Attacks Against Model Fairness.- Federated Bilevel Optimization.- A Two-Stage Stochastic Programming Approach for the Key Management -Composite Scheme.- Recent Advances in Federated Graph Learning.- Privacy in Federated Learning Natural Language Models.- Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs.- Robust Federated Learning for Edge Intelligence.- ZoneFL: Zone-based Federated Learning at the Edge.- Synthetic Data for Privacy Preservation in Distributed Data Analysis Systems.- Towards Green Federated Learning.