Fuzzy Trust Recommendation Based on Collaborative Filtering for Mobile Ad-hoc Networks

Mobile ad-hoc networks (MANETs) are based on cooperative and trust characteristic of mobile nodes. Typically, nodes are both autonomous and self-organized without requiring a central administration or a fixed network infrastructure. Due to their distributed nature, MANETs are very vulnerable to various attacks. To enhance the security of MANETs, it is important to rate the trustworthiness of other nodes without central authorities to build up a trust environment. In this paper, we propose a fuzzy trust recommendation based on collaborative filtering, which stimulates collaboration among distributed computing and communicating nodes, facilitates the detection of untrustworthy nodes, and assists decision-making in various protocols for MANETs. Due to the uncertain interaction outcomes, we use fuzzy logic to model trust recommendation in a MANET environment. Our trust model combines direct trust and trust recommendation information based on collaborative filtering to allow nodes to represent and reason with uncertainty and imprecise information regarding other nodes' trustworthiness. Simulation results show that the proposed model is flexible and valid.