The Neighbor-Trust Metric to Measure Reputation in Organic Computing Systems

Reputation is an important aspect of trust. If no direct trust experiences are available, one needs to rely on reputation data from other sources. In this paper we present the Neighbor-Trust metric that exploits these communication capabilities of a network by directly asking all neighbors of a target communication partner for reputation trust data. This results in a reputation path of length one, but also in a vulnerability to attacks by unknown, lying entities that try to promote not trustworthy entities. However, by adding weights for reputation data given by entities and a learning mechanism the Neighbor-Trust metric is able to identify and adapt to lying participants in the network by reducing the weight their reputation data has in future reputation calculations. We present an evaluation for the metric and show how to exclude lying participants from the network.