Machine Learning-Based Intrusion Detection System for Big Data Analytics in VANET
Mingyuan Zang, Ying Yan
Abstract
Attacks as Distributed Denial of Service (DDoS) are ones of the most frequent vehicle cybersecurity threats. In this paper, we propose a Machine Learning-based Intrusion Detection System (IDS) for monitoring network traffic and detecting abnormal activities. This IDS framework integrates streaming engines for big data analytics, management and visualization. A Vehicular ad-hoc network (VANET) topology of multiple connected nodes with mobility capability is simulated in the Mininet-Wifi environment. Real-time data is collected using the sFlow technology and transmitted from the simulator to our proposed IDS framework. We have achieved high detection accuracy results by training the Random Forest as the classifier to label out the anomalous flows. Additionally, the network throughput has been evaluated and compared with and without deploying the proposed IDS. The results verify the system is a lightweight solution by bringing little burden to the network.