An Extended Hybrid Anomaly Detection System for Automotive Electronic Control Units Communicating via Ethernet - Efficient and Effective Analysis using a Specification- and Machine Learning-based Approach

Daniel Grimm, Marc Weber, Eric Sax

Abstract

Due to the increasing number of functions fulfilled by ECUs in a vehicle, there is a need for new networking technologies offering more bandwidth than e.g. Controller Area Network. Automotive Ethernet is one of the most promising candidates and already used in modern cars. However, currently there is the open issue of detecting and preventing cyber attacks via this well known networking technology. In this paper we present the extension of our hybrid anomaly detection system for ECUs to improve the security and safety of vehicles using Automotive Ethernet. The system combines specification- and machine learning-based anomaly detection methods. The features, necessary for the machine learning part, are selected to enable the detection of anomalies in real-time and with respect to the automotive specific communication scheme. Finally, the detection performance and the applicability of different machine learning algorithms is evaluated in a simulation environment based on synthetic and well defined anomalies.

Download


Paper Citation


in Harvard Style

Weber M., Grimm D. and Sax E. (2018). An Extended Hybrid Anomaly Detection System for Automotive Electronic Control Units Communicating via Ethernet - Efficient and Effective Analysis using a Specification- and Machine Learning-based Approach.In Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-293-6, pages 462-473. DOI: 10.5220/0006779204620473


in Bibtex Style

@conference{vehits18,
author={Marc Weber and Daniel Grimm and Eric Sax},
title={An Extended Hybrid Anomaly Detection System for Automotive Electronic Control Units Communicating via Ethernet - Efficient and Effective Analysis using a Specification- and Machine Learning-based Approach},
booktitle={Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2018},
pages={462-473},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006779204620473},
isbn={978-989-758-293-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - An Extended Hybrid Anomaly Detection System for Automotive Electronic Control Units Communicating via Ethernet - Efficient and Effective Analysis using a Specification- and Machine Learning-based Approach
SN - 978-989-758-293-6
AU - Weber M.
AU - Grimm D.
AU - Sax E.
PY - 2018
SP - 462
EP - 473
DO - 10.5220/0006779204620473