An Ensemble Machine Learning Technique for Detecting Distributed Denial of Service Attacks in Vehicular Ad Hoc Networks

Vehicular Ad-Hoc Networks (VANETs) have the potential to improve road safety and enhance traffic management. Due to their mobility and short-lived network connections, they are vulnerable to a variety of security risks, the most disruptive of which is distributed denial of service (DDoS) attack. This attack can completely take down a network thus depriving road users of crucial services, compromising traffic efficiency, and negatively impacting vehicle safety. This paper presents a mechanism for detecting DDoS attacks on VANETs using machine learning algorithms. The novelty of this work is an ensemble algorithm created by leveraging the strengths of six different ML algorithms to detect DDoS attacks in a VANET environment. The proposed ensemble algorithm performs better or at least comparable to existing solutions on key performance indicators.