Handbook of Trustworthy Federated Learning
暫譯: 可信聯邦學習手冊
Thai, My T., Phan, Hai N., Thuraisingham, Bhavani
- 出版商: Springer
- 出版日期: 2024-09-04
- 售價: $9,810
- 貴賓價: 9.5 折 $9,320
- 語言: 英文
- 頁數: 490
- 裝訂: Hardcover - also called cloth, retail trade, or trade
- ISBN: 303158922X
- ISBN-13: 9783031589225
海外代購書籍(需單獨結帳)
商品描述
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.
商品描述(中文翻譯)
本手冊旨在作為一個一站式的可靠資源,包括精心策劃的調查和關於聯邦學習的解釋性貢獻。它涵蓋了廣泛的主題,為讀者提供技術和非技術的基本知識、應用以及各種主題的詳細資訊。讀者群體從研究人員和學者到深度參與或剛開始探索可信聯邦學習領域的實踐者皆有涵蓋。聯邦學習於2016年首次提出,允許設備在保持原始數據本地化的同時,共同學習共享模型,從而承諾保護數據隱私。自其推出以來,聯邦學習經歷了幾次演變。最重要的是,其演變是對於日益增長的認識的回應,即其協作學習的承諾與隱私保護和模型安全的要求是不可分割的。
該資源分為四個部分。第一部分(安全性與隱私)探討針對目標攻擊的強大防禦機制,並解決公平性問題,為保護聯邦學習系統免受不斷演變的威脅提供多方面的基礎。第二部分(雙層優化)揭示了在聯邦環境中優化性能的複雜性。第三部分(圖形與大型語言模型)解決了訓練圖神經網絡的挑戰以及在自然語言模型的聯邦學習中確保隱私的問題。第四部分(邊緣智能與應用)展示了聯邦學習如何賦能移動應用並利用合成數據保護隱私。
作者簡介
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.
作者簡介(中文翻譯)
My T. Thai 是美國佛羅里達大學計算機與信息科學與工程的研究基金會教授,以及UF Nelms連接世界研究所的副所長。Thai博士在可信AI、安全與隱私、網絡科學和優化方面擁有豐富的專業知識。她已出版7本書籍和300多篇在領先學術期刊和會議上發表的論文,並獲得IEEE、ACM和AAAI的多項最佳論文獎。最近的兩項獎項是AAAI 2023傑出論文獎和2023 ACM網絡科學信任時效獎。Thai博士獲得了多項獎項,包括DTRA青年研究者獎和NSF CAREER獎。此外,Thai博士是多個IEEE國際會議的TPC主席和總主席,並擔任幾本期刊的編輯委員會成員。她目前是《組合優化期刊》(Journal of Combinatorial Optimization, JOCO)、IET區塊鏈期刊的主編,以及Springer優化及其應用系列書籍的編輯。Thai博士是IEEE的會士。
Hai N. Phan 是新澤西理工學院的副教授。Phan博士的研究興趣主要涉及隱私與安全、機器學習、健康信息學、社交網絡分析和時空數據挖掘。Phan博士於2013年10月在蒙彼利埃大學獲得計算機科學博士學位。Phan博士在隱私與安全、機器學習和健康信息學等領域建立了強大的專業知識,發表了47篇以上的論文。其中許多論文發表在領先的會議上,包括ICML、ECML、AAAI、IJCAI、ACM SigSpatial、ACM Multimedia等,並獲得了幾項最佳論文獎,如IEEE ICDM'17、Springer CSoNet'19、Springer CSoNet'18,涉及在深度學習中保持可擴展的差分隱私(DP)和局部差分隱私(LDP),例如自編碼器、卷積神經網絡(CNN)、持續學習和對抗學習、網絡嵌入、語言建模、對模型攻擊的認證穩健性、表示學習和聯邦學習(FL)。
Bhavani Thuraisingham 是德克薩斯大學達拉斯分校計算機科學創始主席教授及網絡安全研究與教育研究所的執行主任。Thuraisingham博士在商業行業(霍尼韋爾)、聯邦資助的研究與發展中心(MITRE)、政府(NSF)和學術界擁有超過35年的工作經驗。她在網絡安全領域進行了三十年的研究,專注於應用數據分析於網絡安全。她的工作已經產生了超過100次的主題演講、120篇期刊論文、300篇會議論文、15本書籍和8項專利。她是ACM、IEEE、AAAS、NAI和IMA的會士。