Automating ecu identification for vehicle security

Michael Jaynes; Ram Dantu; Roland Varriale; Nathaniel Evans

doi:10.1109/ICMLA.2016.53

Automating ecu identification for vehicle security

Michael Jaynes
, Ram Dantu
, Roland Varriale
, Nathaniel Evans

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

26 Scopus citations

Abstract

The field of vehicular cybersecurity has received considerable media and research attention in the past few years. Given the increasingly connected aspect of consumer automobiles, along with the inherent danger of these machines, there has been a call for experienced security researchers to contribute towards the vehicle security domain. The proprietary nature of Controller Area Network (CAN) bus messages, however, creates a barrier of entry for those unfamiliar, due to the need to identify what the messages on a given vehicle's bus are broadcasting. This work aims to automate the process of correlating CAN bus messages with specific Electronic Control Unit (ECU) functions in a new vehicle, by creating a machine learning classifier that has been trained on a dataset of multiple vehicles from different manufacturers. The results show that accurate classification is possible, and that some ECUs that broadcast similar vehicle dynamics broadcast similar CAN messages.

Original language	English
Title of host publication	Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	632-635
Number of pages	4
ISBN (Electronic)	9781509061662
DOIs	https://doi.org/10.1109/ICMLA.2016.53
State	Published - Jan 31 2017
Externally published	Yes
Event	15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016 - Anaheim, United States Duration: Dec 18 2016 → Dec 20 2016

Publication series

Name	Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

Conference

Conference	15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016
Country/Territory	United States
City	Anaheim
Period	12/18/16 → 12/20/16

Funding

The authors would like to thank the National Science Foundation (grant number 1229700) for partially funding this research.

Keywords

Automotive security
CAN bus
Classification
Machine learning

Access to Document

10.1109/ICMLA.2016.53

Cite this

Jaynes, M., Dantu, R., Varriale, R., & Evans, N. (2017). Automating ecu identification for vehicle security. In Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016 (pp. 632-635). Article 7838215 (Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2016.53

Jaynes, Michael ; Dantu, Ram ; Varriale, Roland et al. / Automating ecu identification for vehicle security. Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 632-635 (Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016).

@inproceedings{6b4d1c5ae0ec434e9133af1ad386cabc,

title = "Automating ecu identification for vehicle security",

abstract = "The field of vehicular cybersecurity has received considerable media and research attention in the past few years. Given the increasingly connected aspect of consumer automobiles, along with the inherent danger of these machines, there has been a call for experienced security researchers to contribute towards the vehicle security domain. The proprietary nature of Controller Area Network (CAN) bus messages, however, creates a barrier of entry for those unfamiliar, due to the need to identify what the messages on a given vehicle's bus are broadcasting. This work aims to automate the process of correlating CAN bus messages with specific Electronic Control Unit (ECU) functions in a new vehicle, by creating a machine learning classifier that has been trained on a dataset of multiple vehicles from different manufacturers. The results show that accurate classification is possible, and that some ECUs that broadcast similar vehicle dynamics broadcast similar CAN messages.",

keywords = "Automotive security, CAN bus, Classification, Machine learning",

author = "Michael Jaynes and Ram Dantu and Roland Varriale and Nathaniel Evans",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016 ; Conference date: 18-12-2016 Through 20-12-2016",

year = "2017",

month = jan,

day = "31",

doi = "10.1109/ICMLA.2016.53",

language = "English",

series = "Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "632--635",

booktitle = "Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016",

}

Jaynes, M, Dantu, R, Varriale, R & Evans, N 2017, Automating ecu identification for vehicle security. in Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016., 7838215, Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016, Institute of Electrical and Electronics Engineers Inc., pp. 632-635, 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016, Anaheim, United States, 12/18/16. https://doi.org/10.1109/ICMLA.2016.53

Automating ecu identification for vehicle security. / Jaynes, Michael; Dantu, Ram; Varriale, Roland et al.
Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 632-635 7838215 (Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automating ecu identification for vehicle security

AU - Jaynes, Michael

AU - Dantu, Ram

AU - Varriale, Roland

AU - Evans, Nathaniel

PY - 2017/1/31

Y1 - 2017/1/31

N2 - The field of vehicular cybersecurity has received considerable media and research attention in the past few years. Given the increasingly connected aspect of consumer automobiles, along with the inherent danger of these machines, there has been a call for experienced security researchers to contribute towards the vehicle security domain. The proprietary nature of Controller Area Network (CAN) bus messages, however, creates a barrier of entry for those unfamiliar, due to the need to identify what the messages on a given vehicle's bus are broadcasting. This work aims to automate the process of correlating CAN bus messages with specific Electronic Control Unit (ECU) functions in a new vehicle, by creating a machine learning classifier that has been trained on a dataset of multiple vehicles from different manufacturers. The results show that accurate classification is possible, and that some ECUs that broadcast similar vehicle dynamics broadcast similar CAN messages.

AB - The field of vehicular cybersecurity has received considerable media and research attention in the past few years. Given the increasingly connected aspect of consumer automobiles, along with the inherent danger of these machines, there has been a call for experienced security researchers to contribute towards the vehicle security domain. The proprietary nature of Controller Area Network (CAN) bus messages, however, creates a barrier of entry for those unfamiliar, due to the need to identify what the messages on a given vehicle's bus are broadcasting. This work aims to automate the process of correlating CAN bus messages with specific Electronic Control Unit (ECU) functions in a new vehicle, by creating a machine learning classifier that has been trained on a dataset of multiple vehicles from different manufacturers. The results show that accurate classification is possible, and that some ECUs that broadcast similar vehicle dynamics broadcast similar CAN messages.

KW - Automotive security

KW - CAN bus

KW - Classification

KW - Machine learning

UR - https://www.scopus.com/pages/publications/85015408355

U2 - 10.1109/ICMLA.2016.53

DO - 10.1109/ICMLA.2016.53

M3 - Conference contribution

AN - SCOPUS:85015408355

T3 - Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

SP - 632

EP - 635

BT - Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

Y2 - 18 December 2016 through 20 December 2016

ER -

Jaynes M, Dantu R, Varriale R, Evans N. Automating ecu identification for vehicle security. In Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 632-635. 7838215. (Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016). doi: 10.1109/ICMLA.2016.53

Automating ecu identification for vehicle security

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this