A unified threat-scoring detection algorithm for cybersecurity attacks in automotive CAN networks

Authors

  • Ivan Ivanov Technical university of Varna

DOI:

https://doi.org/10.29114/ajtuv.vol9.iss2.350

Keywords:

CAN bus; in-vehicle network security; threat modeling; intrusion detection

Abstract

Controller Area Network (CAN) is the primary in-vehicle communication backbone but provides no built-in security, leaving vehicles susceptible to message-injection attacks. This study presents a novel algorithm that (1) systematically classifies CAN attack types, (2) computes an impact-weighted probabilistic risk score per attack instance, (3) supplies an on-bus simulation environment for controlled injections, and (4) embeds a lightweight hybrid detector combining an ensemble classifier for known patterns with anomaly scoring for unknown activity. The main contribution is a compact, interpretable scoring model (likelihood × impact × weight) integrated with a reproducible evaluation protocol and reference implementation for benchmarking on public CAN corpora.

Downloads

Download data is not yet available.

References

Bari, B. S., Yelamarthi, K., & Ghafoor, S. (2023). Intrusion detection in vehicle Controller Area Network (CAN) bus using machine learning: A comparative performance study. Sensors, 23(7), 3610.

https://doi.org/10.3390/s23073610

Checkoway, S., McCoy, D., Kantor, B., Anderson, D., Shacham, H., Savage, S., Koscher, K., Czes-kis, A., Roesner, F., & Kohno, T. (2011). Comprehensive experimental analyses of automotive at-tack surfaces. Proceedings of the 20th USENIX Security Symposium, 77–92.

https://dl.acm.org/doi/10.5555/2028067.2028073

International Organization for Standardization. (2015). ISO 11898-1: Road vehicles — Controller area network (CAN) — Part 1: Data link layer and physical signalling. ISO.

https://www.iso.org/standard/63648.html

Kidmose, B., & Meng, W. (2024). can-sleuth: Investigating and evaluating automotive intrusion detection datasets. Proceedings of the European Interdisciplinary Cybersecurity Conference (EICC), 2024. https://doi.org/10.1145/3655693.3655696

Koscher, K., Czeskis, A., Roesner, F., Patel, S., Kohno, T., Checkoway, S., McCoy, D., Kantor, B., Anderson, D., Shacham, H., & Savage, S. (2010). Experimental security analysis of a modern auto-mobile. Proceedings of the 2010 IEEE Symposium on Security and Privacy, 447–462.

https://doi.org/10.1109/SP.2010.34

Lampe, B., & Meng, W. (2024). can-train-and-test: A curated CAN dataset for automotive intrusion detection. Computers & Security, 140, Article 103777.

https://doi.org/10.1016/j.cose.2024.103777

Miller, C., & Valasek, C. (2015). Remote exploitation of an unaltered passenger vehicle. Black Hat USA, 1–91.

https://www.scirp.org/reference/referencespapers?referenceid=2387001

Müter, M., Groll, A., & Freiling, F. C. (2011). A structured approach to anomaly detection for in-vehicle networks. Proceedings of the 2011 Sixth International Conference on Availability, Reliability and Security, 237–242.

https://doi.org/10.1109/isias.2010.5604050

Pinto, A., Herrera, L.-C., Donoso, Y., & Gutiérrez, J. A. (2023). Survey on intrusion detection sys-tems based on machine learning techniques for the protection of critical infrastructure. Sensors, 23(5), 2415.

https://doi.org/10.3390/s23052415

Qin, H., Yan, M., & Ji, H. (2021). Application of Controller Area Network (CAN) bus anomaly de-tection based on time series prediction. Vehicular Communications, 27, Article 100291.

https://doi.org/10.1016/j.vehcom.2020.100291

Downloads

Published

2025-12-30

How to Cite

Ivanov, I. (2025). A unified threat-scoring detection algorithm for cybersecurity attacks in automotive CAN networks. ANNUAL JOURNAL OF TECHNICAL UNIVERSITY OF VARNA, BULGARIA, 9(2), 61–69. https://doi.org/10.29114/ajtuv.vol9.iss2.350

Issue

Section

INFORMATION TECHNOLOGIES, COMMUNICATION AND COMPUTER EQUIPMENT

Similar Articles

1 2 > >> 

You may also start an advanced similarity search for this article.