A Reputation System Using a Bayesian Statistical Filter in Vehicular Networks

The rapid development of wireless technologies has led to the emergence of new types of highly dynamic networks with centralized and decentralized architectures. Vehicular networks (VANETs) technology is one of those networks. The communication between vehicles will lead to more efficient and secured roads by providing information about traffic and road conditions to vehicle drivers. In order to protect vehicle passengers and drivers, these networks need a secure infrastructure to prevent malicious behavior from happening. This paper proposes a strong reputation system based on a Bayesian statistical filter to detect malicious nodes which drop packets selectively or completely in VANETs. The proposed approach allows vehicles to interact in order to detect the malicious one, give it a bad reputation and exclude it from the network.