Costs of protecting privacy in agent trust relationships

Abstract

In this paper we remarked the relevance of using of privacyprotection measures in trust models, since them imply conscious exchanges of opinions about third parties. Additionally to the already published description of the extra message exchanges that would protect privacy in a agent-mediated trust domain as ART testbed, we evaluate (through estimated weights) the communication and computation cost of these additional message exchanges at the level of their interactions. Although the effects of introducing them on the accuracy of trust valuations could also be considered in future works, in this contribution we focus our attention in an approach based on the weight of the information brought by an interaction.