Towards a Generic Trust Management Framework Using a Machine-Learning-Based Trust Model

Nowadays, the ever-growing capabilities in computer communication networks have entitled and encouraged developers and researchers to build collaborative applications, systems, and devices. On the one hand with increased collaboration, several advantages have been obtained, but, on the other hand, issues may arise due to untrustworthy interactions. To address these issues, many researchers have studied trust as a computer science concept. Nevertheless, one of the greatest challenges in the trust domain is the lack of a generic trust management framework that will ease and encourage existing collaborative systems to adopt such concepts. In this paper, we propose a generic trust management framework which is capable of processing different trust features as required. We propose a RESTful message exchanging architecture, and a trust model based on the solution of a multi-class classification problem using machine learning techniques, namely Support Vector Machines(SVM).