04431nam a22005655i 4500 978-3-031-58013-0 DE-He213 20251030112246.0 cr nn 008mamaa 240531s2024 sz | s |||| 0|eng d 9783031580130 978-3-031-58013-0 10.1007/978-3-031-58013-0 doi TK5101-5105.9 TJK bicssc TEC041000 bisacsh TJK thema Zhang, Guanglin. author. aut http://id.loc.gov/vocabulary/relators/aut 77952 Privacy Preservation in Distributed Systems [electronic resource] : Algorithms and Applications / by Guanglin Zhang, Ping Zhao, Anqi Zhang. 1st ed. 2024. Cham : Springer Nature Switzerland : Imprint: Springer, 2024. XIV, 256 p. 93 illus., 92 illus. in color. online resource. text txt rdacontent computer c rdamedia online resource cr rdacarrier text file PDF rda Signals and Communication Technology, 1860-4870 Introduction -- Part I Privacy lssues in Data Aggregation -- LocMIA: Membership Inference Attacks against Aggregated Location Data -- Synthesizing Privacy Preserving Traces: Enhancing Plausibility with Social Networks -- DAML: Practical Secure Protocol for Data Aggregation based Machine Learning -- Enhancing Privacy Preservation in Speech Data Publishing -- Part II Privacy Issues in Indoor Localization -- Lightweight Privacy-Preserving Scheme in WiFi Fingerprint-Based Indoor Localization -- P3LOC: A Privacy-Preserving Paradigm-Driven framework for Indoor Localization -- Preserving Privacy in WiFi Localization with Plausible Dummy Locations -- Part III Privacy-Preserving Offloading in MEC -- Deep Reinforcement Learning-based Joint Optimization of Delay and Privacy in Multiple-User MEC Systems -- Load Balancing for Energy-Harvesting Mobile Edge Computing -- Learning-based Joint Optimization of Energy-Delay and Privacyin Multiple-User Edge-Cloud Collaboration MEC Systems. This book provides a discussion of privacy in the following three parts: Privacy Issues in Data Aggregation; Privacy Issues in Indoor Localization; and Privacy-Preserving Offloading in MEC. In Part 1, the book proposes LocMIA, which shifts from membership inference attacks against aggregated location data to a binary classification problem, synthesizing privacy preserving traces by enhancing the plausibility of synthetic traces with social networks. In Part 2, the book highlights Indoor Localization to propose a lightweight scheme that can protect both location privacy and data privacy of LS. In Part 3, it investigates the tradeoff between computation rate and privacy protection for task offloading a multi-user MEC system, and verifies that the proposed load balancing strategy improves the computing service capability of the MEC system. In summary, all the algorithms discussed in this book are of great significance in demonstrating the importance of privacy. Addresses privacy concerns related to Data Aggregation, Indoor Localization, and Mobile Edge Computing; Introduces innovative solutions and algorithms to tackle privacy challenges; Offers readers a forward-looking perspective into future developments and challenges in privacy research. Telecommunication. Computational intelligence. 64052 Machine learning. 55059 Communications Engineering, Networks. Computational Intelligence. 64052 Machine Learning. 55059 Zhao, Ping. author. aut http://id.loc.gov/vocabulary/relators/aut 77953 Zhang, Anqi. author. aut http://id.loc.gov/vocabulary/relators/aut 77954 SpringerLink (Online service) Springer Nature eBook Printed edition: 9783031580123 Printed edition: 9783031580147 Printed edition: 9783031580154 Signals and Communication Technology, 1860-4870 18936 https://doi.org/10.1007/978-3-031-58013-0 ZDB-2-ENG ZDB-2-SXE 60348 60348