Machine Unlearning: Concepts and Implementations

Weiqi Wang · Shui Yu

2026년 8월 · Springer Nature

eBook

143

페이지

eBook 정보

As "right to be forgotten" style regulations, data governance requirements, and security concerns expand worldwide, researchers and practitioners need methods that go beyond ad hoc retraining and provide effective deletion from models. Machine unlearning has emerged as a core capability for trustworthy artificial intelligence (AI), enabling trained models to remove the influence of specific data after deployment. This book offers a systematic, end to end guide to machine unlearning, from foundational problem formulations to practical design patterns for real world systems. It introduces the unlearning paradigm and key evaluation criteria, then presents a structured treatment of exact unlearning and approximate unlearning, highlighting when each is appropriate and what trade-offs arise in utility, efficiency, and reliability. A dedicated section on unlearning auditing and verification explains how to test and validate deletion claims, including protocol level schemes, model centric auditing approaches, and benchmark driven stress testing at scale. The book then extends unlearning to domain specific settings, covering graph unlearning, federated unlearning, and emerging techniques for large language models and diffusion models. Finally, it examines privacy and security risks such as leakage, backdoors, and poisoning, and surveys defenses and future directions for building dependable unlearning services. Written for graduate students, researchers, and engineers, the book provides a coherent taxonomy, practical insights, and a roadmap for developing, evaluating, and deploying unlearning in modern AI pipelines.

콘텐츠 둘러보기

저자 정보

Dr. Weiqi Wang is a postdoc at University of Technology Sydney. He received his PhD degree with the School of Computer Science, University of Technology Sydney, advised by Professor Shui Yu. He previously worked as a senior algorithm engineer at the Department of AI-Strategy, Local Consumer Services Segment, Alibaba Group. He has been actively involved in the research community by serving as a reviewer for prestige journals such as ACM Computing Surveys, IEEE Communications Surveys and Tutorials, IEEE TIFS, IEEE TDSC, IEEE TIP, IEEE TMC, IEEE Transactions on SMC, and IEEE IOTJ, and international conferences such as ICML, CVPR, WWW, ICLR, IEEE ICC, and IEEE GLOBECOM. His research interests focus on security and privacy for trustworhty AI.

Prof. Shui Yu is currently a Professor of School of Computer Science, Deputy Chair of University Research Committee, University of Technology Sydney, Australia. His research interest includes Mathematical AI, Cybersecurity, Network Science, and Big Data. He has published seven monographs and edited two books, more than 650 technical papers at different venues. His current h-index is 86. Professor Yu promoted the research field of networking for big data since 2013, and his research outputs have been widely adopted by industrial systems, such as Amazon cloud security. He is currently serving the editorial boards of IEEE Communications Surveys and Tutorials (Area Editor), IEEE Transactions on Cognitive Communications and Networking, and IEEE Transactions on Dependable and Secure Computing. He is a Distinguished Visitor of IEEE Computer Society, and an elected member of the Board of Governors of IEEE Communications Society. He is a member of ACM and AAAS, and a Fellow of IEEE.