Capturing reputation features in multiagent systems through emerging patterns

Multiagent systems and online communities rely on rating systems to infer the reputation given to an individual within a particular context. The notion of reputation is essential for helping a given individual to trust in other individuals and for being himself reliable to others. Current techniques for computing individual’s reputations are solely based on recent activities, facilitating a variety of possible attacks. Moreover, the amount of trust each agent has for a given context is based just on his or her reputation. In this paper we outline a new way to thwart reputation-based attacks and to detect trends in behavioral patterns based on historical data by means of knowledge discovery techniques, particularly those existing for emerging patterns. Eje: Inteligencia artificial Red de Universidades con Carreras en Informática (RedUNCI)