Trust is an essential component for secure collaboration in uncertain environments. Trust management can be used to reason about future interactions between entities. In reputation-based trust management, an entity’s reputation is usually 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 different aspects of an entity’s behavior, we use multi-dimensional application specific trust values and each dimension is evaluated using a single Bayesian network. This makes it easy both to extend the model to involve more dimensions of trust and to combine Bayesian networks to form an opinion about the overall trustworthiness of an entity. Each entity can evaluate his peers according to his own criteria. The dynamic characteristics of criteria and of peer behavior can be captured by updating Bayesian networks. Risk is explicitly combined with trust to help users making decisions. In this paper, we show that our system can make accurate trust inferences and is robust against unfair raters.