Article citationsMore>>

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

has been cited by the following article:

• TITLE: An Enhanced and Explainable Hybrid Ensemble Intrusion Detection System for Connected Vehicles

  AUTHORS: Xuemei Li, Rui Zhu, Huirong Fu

  KEYWORDS: Hybrid Ensemble Intrusion Detection System, MLP, Vehicle Networks, Cybersecurity, Explainable AI

  JOURNAL NAME: Journal of Information Security, Vol.16 No.3, July 7, 2025

  ABSTRACT: 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.