IoT trust aggregation using hybrid outlier detection and consensus

Abstract

Trust modelling and management strategy used identify and mitigate threats by malicious devices rely on peer recommendations to compute trustworthiness. Aggregating opinions from independent devices is crucial in such recommendation-based systems to arrive at a consensus for decision making. Existing aggregation techniques like arithmetic mean, geometric mean (weighted/non-weighted), and maximum/minimum functions ignore the risk of biased and uncertain recommendations. To encounter such vulnerabilities, we propose a novel trust assessment model, outlier and uncertain recommendation-based trust management (OUR-Trust). It uses an outlier elimination and similarity-based scheme to evaluate the recommender's credibility before aggregation for consensus and decision making. The model employs revised Dempster-Shaffer combination rule for aggregation, which considers the uncertainty factor. Effectiveness of proposed approach is analysed for a dynamic and heterogeneous IoT network of dynamic and heterogeneous devices. OUR-Trust is validated for storage, power-efficiency, and scalability in terms of convergence time for more extensive IoT networks that employ recommender systems.