Synthesizing datasets with security threats for vehicular ad-hoc networks

Abstract

Vehicular Ad hoc Networks (VANETs) are the underlying network for all the communications between Intelligent Transportation System entities as, for example, Road Side Units, On-Board Units, etc. These networks are growing in size and interest from the automaker's industry, software companies and scientific researchers. The intrinsic technological nature of VANETs (based on a wireless shared medium) with no predefined structure of architecture (high mobility of their users) makes them very susceptible to security attacks, which may impact deeply on road users. There are several works on VANET security, usually involving cryptography. But, these can only prevent some types of attacks. Others, mainly the ones carried by authentic entities, cannot be prevented applying this strategy. Nonetheless, attacks can be detected triggering responses minimizing the repercussions. This can be accomplished by using an Intrusion Detection System (IDS) which can be enhanced with the help of Machine Learning (ML). But, one of the main difficulties for an effective implementation of a ML-based IDSs is the (un)availability of valid public datasets. The IDSs need a large collection of VANET messages to be able to recognize types of behaviors. However, most of the studies in the literature discussing solutions and their results do not make the datasets publicly available for scrutiny by third parties. As such, the results are difficult to properly verify and validate. The goal of this work is to provide well documented and publicly available datasets to be used by researchers on future RD projects, enabling a fairer comparison of their results.