Distributed Neural Network-Based DDoS Detection in Vehicular Communication Systems

As modern vehicular communication systems advance, the demand for robust security measures becomes increasingly critical. A misbehavior detection systems (MDS) is a tool developed to detect if a vehicular network is being attacked so that the system can take steps to mitigate harm from the attacker. Vehicular communication systems face significant risks from distributed denial of service (DDoS) attacks. During a DDoS attack, multiple nodes are used to flood the target with an overwhelming amount of communication packets. In this paper, we first survey the current MDS literature and how it is used to detect and mitigate DDoS attacks. We then propose a new distributed multilayer perceptron classifier (MLPC) for DDoS detection and evaluate the performance of the proposed detection scheme in vehicular communication systems. For the evaluations using simulations, two specific implementations of the attacks are conducted. Apache Spark is then used to create the distributed MLPC. The median F1-score for this MLPC method was 95%. The proposed method outperformed linear regression and support vector machines, which achieved 89% and 88% respectively, but is unable to perform better than random forests and gradient boosted trees which both achieved a 97% F1-score. Using Amazon Web Services (AWS), it is determined that model training and detection time are not significantly increased with the inclusion of additional nodes after three nodes including the master.