Bayesian network based trust management

Abstract

Trust is an essential component for secure collaboration in uncertainenvironments. Trust management can be used to reason about future interactionsbetween entities. In reputation-based trust management, an entity’s reputation isusually built on ratings from those who have had direct interactions with the entity.In this paper, we propose a Bayesian network based trust management model.In order to infer trust in dierent aspects of an entity’s behavior, we use multidimensionalapplication specific trust values and each dimension is evaluated usinga single Bayesian network. This makes it easy both to extend the model toinvolve more dimensions of trust and to combine Bayesian networks to form anopinion about the overall trustworthiness of an entity. Each entity can evaluate hispeers according to his own criteria. The dynamic characteristics of criteria and ofpeer behavior can be captured by updating Bayesian networks. Risk is explicitlycombined with trust to help users making decisions. In this paper, we show thatour system can make accurate trust inferences and is robust against unfair raters.