A Novel Recommendation-Based Trust Inference Model for MANETs

Over the last few years, trust, security, and privacy in mobile ad hoc networks have received increasing attention. The proposed trust-based countermeasures are considered to be promising approaches, which play an important role for reliable data transmission, qualified services with context-awareness, and information security. The foundation of these countermeasures is trust computation. In order to address this issue, we first study trust properties, and subsequently abstract a novel recommendation-based trust inference model. Two trust attributes called the subjective trust and the recommendation trust, are selected to quantify the trust level of a specific entity. Recommendations provide an effective way to build trust relationship, by making use of the information from others rather than exclusively relying on one's own direct observation. To compute the subjective trust and the recommendation trust precisely, some comprehensive factors are introduced. Furthermore, the concept of belief factor is proposed to integrate these two trust attributes. The aim of this trust model is, the network can itself detect, prevent and exclude the misbehaving entities, and obtain strong resistibility to malicious attacks as well. The effectiveness and resistibility of the model are analyzed theoretically and evaluated experimentally. The experimental results show that this new mechanism outperforms existing mechanisms.