Real-time driver behaviour characterization through rule-based machine learning

Modern car-embedded technologies enabled car thieves to perform new ways to steal cars. In order to avoid auto-theft attacks, in this paper we propose a machine learning based method to silently and continuously profile the driver by analyzing built-in vehicle sensors. The proposed method exploits rule-based machine learning with the aim to discriminate between the car owner and impostors. Furthermore, we discuss how the rules generated by the rule-based algorithm can be adopted in order to discriminate between different driving styles.