Abstract
With the emerging wireless technology integrated into modern vehicles, this introduces an enormous number of vulnerabilities for adversaries to compromise the vehicle internal system. Nonetheless, the attacks can be alleviated using anomaly detection mechanism which have been proven to be effective in monitoring and detecting attacks. In this paper, we developed an anomaly detection using an unsupervised deep learning-based approach, known as Deep Contractive Autoencoders (DCAEs). The DCAEs, which is one of the regularize autoencoders model imposed a different penalty term to the CAN data representation in order to encourage robustness towards small changes. To accomplish this purpose, we captured CAN bus data from three different vehicles, pre-processed them using the max absolute normalization, and evaluated the model over three types of attacks. Finally, the experimental results demonstrated that DCAEs yield a 91–100% detection rate which outperformed other variants of regularized autoencoders.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Miller, C., Valasek, C.: A survey of remote automotive attack surfaces. Black hat USA (2014)
Li, J.: CANsee-an automobile intrusion detection system. In: Presentation Slides on Hack In The Box Security Conference (HITBSecConf) (2016)
Checkoway, S., McCoy, D., Kantor, B., Anderson, D., Shacham, H., Savage, S.,… Kohno, T.: Comprehensive experimental analyses of automotive attack surfaces. In: USENIX Security Symposium vol. 4, (2011, August)
Koscher, K., Czeskis, A., Roesner, F., Patel, S., Kohno, T., Checkoway, S.,… Savage, S.: Experimental security analysis of a modern automobile. In: 2010 IEEE Symposium on Security and Privacy, pp. 447–462. IEEE (2010, May)
Kang, M.J., Kang, J.W.: Intrusion detection system using deep neural network for in-vehicle network security. PLoS ONE 11(6), e0155781 (2016)
Taylor, A., Leblanc, S., Japkowicz, N.: Anomaly detection in automobile control network data with long short-term memory networks. In: 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 130–139. IEEE (2016, October)
Wasicek, A., Weimerskirch, A.: Recognizing manipulated electronic control units. No. 2015–01-0202. SAE Technical Paper (2015)
Lokman, S.F., Othman, A.T., Abu-Bakar, M.H.: Intrusion detection system for automotive Controller Area Network (CAN) bus system: a review. EURASIP J. Wirel, Commun. Netw. 2019(1), 184 (2019)
Farhana Lokman, S., Talib Othman, A., Husaini Abu Bakar, M., Razuwan, R.: Stacked sparse autoencoders-based outlier discovery for in-vehicle controller area network (CAN). Int. J. Eng. & Technol., 7(4.33), 375–380 (2018). http://dx.doi.org/10.14419/ijet.v7i4.33.26078
Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contractive auto-encoders: explicit invariance during feature extraction. In: Proceedings of the 28th International Conference on International Conference on Machine Learning, pp. 833–840. Omnipress (2011, June)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096–1103. ACM (2008, July)
An, J., Cho, S.: Variational autoencoder based anomaly detection using reconstruction probability. Spec Lect IE 2, 1–18 (2015)
Lehmann, E.L., Casella, G.: Theory of Point Estimation. Springer Science & Business Media (2006)
Willmott, C.J., Matsuura, K.: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Res. 30(1), 79–82 (2005)
Acknowledgments
This study was supported by the Short-Term Research Grant (grant number str17001), funded by the Center for Research and Innovation, Universiti of Kuala Lumpur and System Engineering and Energy Laboratory (SEELab).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Lokman, S.F., Othman, A.T., Musa, S., Abu Bakar, M.H. (2019). Deep Contractive Autoencoder-Based Anomaly Detection for In-Vehicle Controller Area Network (CAN). In: Abu Bakar, M., Mohamad Sidik, M., Öchsner, A. (eds) Progress in Engineering Technology. Advanced Structured Materials, vol 119. Springer, Cham. https://doi.org/10.1007/978-3-030-28505-0_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-28505-0_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-28504-3
Online ISBN: 978-3-030-28505-0
eBook Packages: Chemistry and Materials ScienceChemistry and Material Science (R0)