Machine learning approach for multiple misbehavior detection in VANET

Abstract

The motivation behind Vehicular Ad Hoc Networks (VANETs) is to improve traffic safety and driving efficiency. VANET applications operate on the principle of periodic exchange of messages between nodes. However, a malicious node may transmit inaccurate messages to trigger inevitable situations. Each transmitted packet contains the status of sender like its identity, position and time of sending the packet in addition to safety message. A misbehaving node may tamper with any information present in the propagated packet. Fake messages may be created by attacker node itself or it may force another node to create fake messages. In this paper, we present a machine learning approach to classify multiple misbehaviors in VANET using concrete and behavioral features of each node that sends safety packets. A security framework is designed to differentiate a malicious node from legitimate node. We implement various types of misbehaviors in VANET by tampering information present in the propagated packet. These misbehaviors are classified based upon multifarious features like speed-deviation of node, received signal strength (RSS), number of packets delivered, dropped packets etc. Two types of classification accuracies are measured: Binary and Multi-Class. In Binary classification, all types of misbehaviors are considered to be in a single "misbehavior" class whereas, Multi-class classification is able to categorize misbehaviors into particular misbehaving classes. Features of packet sending nodes are extracted by performing experiments in NCTUns-5.0 simulator with different simulation scenario (varying the number of legitimate and misbehaving nodes). Proposed framework for classification of misbehavior is evaluated using WEKA. Our approach is efficient in classifying multiple misbehaviors present in VANET scenario. Experiment result shows that Random Forest and J-48 classifiers perform better compared to other classifiers. © 2011 Springer-Verlag.