Intelligent vehicles require strong cybersecurity. The 2021 UNECE WP.29 regulation mandates OEMs to establish Vehicle Security Operation Centers (VSOC), where Intrusion Detection Systems (IDS) are essential. Due to limited computing resources on in-vehicle units, offloading data to edge or cloud is preferred. This paper proposes a Hybrid Ensemble MLP IDS (HE-MLP IDS) combining auto-encoder-based feature extraction, ensemble neural networks, and weighted voting. Evaluated with varying architectures and explained using XAI, the model achieves 0.99 accuracy, recall, and F1-score, with a 7.8e？4 false alarm rate. It outperforms benchmarks in memory size and prediction speed, while effectively identifying attack-relevant features from CAN and network logs.
References
[1]
Andrew, M. (2020) Business Insider Intelligence. https://www.businessinsider.com/iot-connected-smart-cars
[2]
Dibaei, M., Zheng, X., Jiang, K., Abbas, R., Liu, S., Zhang, Y., et al. (2020) Attacks and Defences on Intelligent Connected Vehicles: A Survey. Digital Communications and Networks, 6, 399-421. https://doi.org/10.1016/j.dcan.2020.04.007
[3]
Schultz, M.G., Eskin, E., et al. (2001) Data Mining Methods for Detection of New Malicious Executables. Proceedings 2001 IEEE Symposium on Security and Privacy, Oakland, 14-16 May 2000, 38-49.
[4]
Auroralabs (2021) OTA Update Cost Considerations. Aurora Labs OTA Update Cost Considerations. https://www.automotive.auroralabs.com/ota-guide-viewer/
[5]
Anyanwu, G.O., Nwakanma, C.I., Kim, J., Lee, J. and Kim, D. (2022) Misbehavior Detection in Connected Vehicles Using Burst-Adma Dataset. 2022 13th International Conference on Information and Communication Technology Convergence, Jeju Island, 19-21 October 2022, 874-878. https://doi.org/10.1109/ictc55196.2022.9952947
[6]
Amanullah, M.A., Baruwal Chhetri, M., Loke, S.W. and Doss, R. (2022). Burst-Adma: Towards an Australian Dataset for Misbehaviour Detection in the Internet of Vehicles. 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and Other Affiliated Events (PerCom Workshops), Pisa, 21-25 March 2022, 624-629. https://doi.org/10.1109/percomworkshops53856.2022.9767505
[7]
Aloqaily, M., Otoum, S., Ridhawi, I.A. and Jararweh, Y. (2019) An Intrusion Detection System for Connected Vehicles in Smart Cities. Ad Hoc Networks, 90, Article 101842. https://doi.org/10.1016/j.adhoc.2019.02.001
[8]
Kang, M. and Kang, J. (2016) Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security. PLOS ONE, 11, e0155781. https://doi.org/10.1371/journal.pone.0155781
[9]
Song, H.M., Woo, J. and Kim, H.K. (2020) In-Vehicle Network Intrusion Detection Using Deep Convolutional Neural Network. Vehicular Communications, 21, Article 100198. https://doi.org/10.1016/j.vehcom.2019.100198
[10]
Seo, E., Song, H.M. and Kim, H.K. (2018) GIDS: GAN Based Intrusion Detection System for In-Vehicle Network. 2018 16th Annual Conference on Privacy, Security and Trust (PST), Belfast, 28-30 August 2018, 1-6. https://doi.org/10.1109/pst.2018.8514157
[11]
Yang, L., Moubayed, A., Hamieh, I. and Shami, A. (2019) Tree-Based Intelligent Intrusion Detection System in Internet of Vehicles. 2019 IEEE Global Communications Conference (GLOBECOM), Waikoloa, 9-13 December 2019, 1-6. https://doi.org/10.1109/globecom38437.2019.9013892
[12]
Yang, L., Moubayed, A. and Shami, A. (2022) MTH-IDS: A Multitiered Hybrid Intrusion Detection System for Internet of Vehicles. IEEE Internet of Things Journal, 9, 616-632. https://doi.org/10.1109/jiot.2021.3084796
[13]
Teng, S., Wu, N., Zhu, H., Teng, L. and Zhang, W. (2018) SVM-DT-Based Adaptive and Collaborative Intrusion Detection. IEEE/CAA Journal of Automatica Sinica, 5, 108-118. https://doi.org/10.1109/jas.2017.7510730
[14]
Ganaie, M.A., Hu, M.H., et al. (2022) Ensemble Deep Learning: A Review. Engineering Applications of Artificial Intelligence, 115, Article 105151.
[15]
Shah, B. and H Trivedi, B. (2012) Artificial Neural Network Based Intrusion Detection System: A Survey. International Journal of Computer Applications, 39, 13-18. https://doi.org/10.5120/4823-7074
Salo, F., Injadat, M., et al. (2020) Data Mining with Big Data in Intrusion Detection Systems: A Systematic Literature Review.
[18]
Lundberg, S.M. and Lee, S.-I. (2017) A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 4768-4777.
[19]
Sharafaldin, I., Habibi Lashkari, A. and Ghorbani, A.A. (2018) Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization. Proceedings of the 4th International Conference on Information Systems Security and Privacy, Madeira, 22-24 January 2018, 108-116.
