Conclusion and Future Research Issues

The research presented in this monograph mainly focuses on privacy preservation issues in the edge computing paradigm in terms of data utility, privacy protection level, and efficiency of privacy preservation. This monograph consists of five chapters. We first study the current research backgrounds of edge computing and its privacy issues by analyzing the privacy challenges that exist in the edge computing paradigm. According to the challenges, this monograph focuses on the improvement and analysis of the overall paradigm in edge computing at the beginning. Second, based on the solid foundation that was developed, we discuss context-aware privacy issues at the end by proposing a MDP-based mechanism with SARSA reinforcement learning capabilities to archive optimal tradeoffs while enhancing the data utility and privacy level. Furthermore, we concentrate on privacy issues for location-aware applications by proposing a dual-scheme privacy protection model against multiple attacking scenarios. Moreover, we propose a novel decentralized blockchain-enabled federated learning (FL-Block) scheme which allows privacy-preserving local learning updates of end devices exchanges with blockchain-based global learning model.