A Distributed Trust and Reputation Framework for Scientific Grids

Acknowledged as important factors for business environments operating as Virtual Organizations (VOs), trust and reputation are receiving attention also in Grids devoted to scientific applications where problems of finding suitable models and architectures for flexible security management of heterogeneous resources arise. Being these resources highly heterogeneous (from individual users to whole organizations or experiment tools and workflows), this paper presents a trust and reputation framework that integrates a number of information sources to produce a comprehensive evaluation of trust and reputation by clustering resources having similar capabilities of successfully executing a specific job. Here, trust and reputation are considered as Quality of Service (QoS) parameters, and are asserted on the operative context of resources, a concept expressing the resources capability of providing trusted services within collaborative scientific applications. Specifically, the framework exploits the use of distributed brokers that support interaction trust and the creation of VOs from existing scientific organizations. A broker is a distributed software module launched at some node of the Grid that makes use of resources and communicates with other brokers to perform specific reputation services. In turn, each broker contributes to maintain a dynamic and adaptive reputation assessment within the Grid in a collaborative and distributed fashion. The proposed framework is empirically implemented by adopting a SOA approach and results show its effectiveness and its possible integration in a scientific Grid