A multi-dimensional trust model for misbehavior detection in vehicular ad hoc networks

Abstract

Communication security is one of the focus issues of vehicular ad hoc networks (VANETs). Trust model is commonly used to identify malicious attackers or filter false messages in the network, which effectively guarantees secure communication between vehicles. Constrained by the distributed network architecture of VANETs, trust evaluation results may be biased due to uneven data distribution and lack of reference. By colluding with the partners, malicious vehicle launches imbalance attack and zigzag attack to bypass the detection of the trust model. To address these new intelligent attacks, we propose a multi-dimensional trust model (MDT) in this paper, which makes a combined evaluation of different trust attributes from vehicles. In MDT, data collection and trust calculation are deployed in vehicles and trust authority (TA), respectively. Since the model dynamically adjusts the corresponding weight coefficient according to the data fluctuations of each trust indicator by adopting entropy weight method and filters anomalous evaluation results by using the median absolute deviation (MAD) algorithm, it can effectively deal with complex and variable intelligent attacks. The legitimate identity of a vehicle will be revoked from the network by TA once its trust value is less than the threshold. We have conducted extensive experimental studies to evaluate the performance of MDT. The experimental results show that the MDT model can accurately and effectively calculate the global trust of vehicles and detect malicious attacks in the network under different scenarios and tests.