Salta al contenuto principale
Passa alla visualizzazione normale.


A simulation framework for evaluating distributed reputation management systems


In distributed environments, where interactions involve unknown entities, intelligent techniques for estimating agents’ reputation are required. Reputation Management Systems (RMSs) aim to detect malicious behaviors that may affect the integrity of the virtual community. However, these systems are highly dependent of the application domain they address; hence the evaluation of different RMSs in terms of correctness and resistance to security attacks is frequently a tricky task. In this work we present a simulation framework to support researchers in the assessment of a RMS. The simulator is organized in two logic layers where network nodes are mapped to system processes that implement the interactions between the agents. Message Passing Interface (MPI) is used to enable communication among different distributed processes and provide the synchronization within the framework. A case study addressing the simulation of two different attacks to a RMS is also presented.