Nowadays we are faced with an increasing popularity of social software including wikis, blogs, micro-blogs and online social networks such as Facebook and MySpace. Unfortunately, the mostly used social services are centralized and personal information is stored at a single vendor. This results in potential privacy problems as users do not have much control over how their private data is disseminated. To overcome this limitation, some recent approaches envisioned replacing the single authority centralization of services by a peer-to-peer trust-based approach where users can decide with whom they want to share their private data. In this peer-to-peer collaboration it is very difficult to ensure that after data is shared with other peers, these peers will not misbehave and violate data privacy. In this paper we propose a mechanism that addresses the issue of data privacy violation due to data disclosure to malicious peers. In our approach trust values between users are adjusted according to their previous activities on the shared data. Users share their private data by specifying some obligations the receivers must follow. We log modifications done by users on the shared data as well as the obligations that must be followed when data is shared. By a log-auditing mechanism we detect users that misbehaved and we adjust their associated trust values by using any existing decentralized trust model.
Evidential Trust-Aware Model Personalization in Decentralized Federated Learning for Wearable IoT
Quantum Cloud Computing and Distributed Systems (qCLOUDS) Lab（量子云计算与分布式系统实验室）；School of Computing and Information Systems（计算与信息系统学院）；The University of Melbourne, Australia（墨尔本大学）
