Probabilistic Trust Management in Pervasive Computing

In this paper, we propose a probabilistic trust management approach for pervasive computing environment. The approach considers trust value as a probability that a device provides satisfactory interactions with its neighbors. A distributed trust management using recommendation was constructed. An iterative filtering method is employed to eliminate the effect of false recommendations while the weighting method is employed to capture the effect of time on the current behavior of devices. We have carried out performance evaluations using simulation experiments. The comparison made with a deterministic trust management scheme demonstrated that the probabilistic trust management approach performs better, than the deterministic approach while also ensuring the security of interactions, and quickly adapting to changes in the environment.