Highly accurate sybil attack detection in vanet using extreme learning machine with preserved location

Due to the development of transportation technology, the number of vehicles on the road has been exponential over the years. Road safety is one of the crucial tasks of the transportation department because of collations and accidents each year. Using a Vehicular ad hoc network (VANET) makes communication between vehicles possible and reduces the complexities in vehicle transportation. Privacy is one of the significant tasks in the VANET for a safe and uninterrupted transportation process. Sybil attack is one of the significant issues in the VANET in which attackers introduce dummy nodes to confuse or interrupt the other users in the network to reduce the performance to hack the data. This work proposes a new technique to detect and disconnect Sybil from the network to improve its performance. Historical and statistical data with Extreme Learning Machine is used to classify the Sybil attack in the VANET. This work improved the classification accuracy and network performance compared to the conventional Sybil node identification technique.

Automated summary

Due to the exponential increase in the number of vehicles on the road, road safety is a crucial task. Vehicular ad hoc networks (VANETs) allow communication between vehicles and reduce transportation complexities. Maintaining privacy is important for uninterrupted and secure transportation. The proposed technique in this study improves the classification accuracy and network performance by using historical and statistical data with Extreme Learning Machines for detecting Sybil attacks in VANETs.