A dynamic data driven-based semi-distributed reputation mechanism in unknown networks

Trust is a crucial concern related to unknown networks. A mechanism that distinguishes trustworthy and untrustworthy nodes is essential. The effectiveness of the mechanism depends on the accuracy of a node's reputation. The dynamics of trust often occurs in a trusted network and causes intoxication and disguises of the nodes, resulting in abnormal behaviors. This study proposes a semi-distributed reputation mechanism based on a dynamic data-driven application system. This mechanism includes two reputations, local reputation (LRep) and global reputation (GRep). LRep is dynamically and selectively injected into a central controller, and this controller collects the injected data to compute GRep, which contains the neural network prediction method, and returns it to provide reference to the distributed nodes. The proposed mechanism focuses on dynamics of trust and the balance between distributed nodes and the central controller. Experimental results showed that GRep was computable with only 52.21% (average) LReps upload and that GRep increased or reduced by 26.5% (average) in a short period, demonstrating that the proposed mechanism effectively handles the problem of dynamics of trust.