LCSMC-Net: Lightweight CAN Intrusion Detection via Separable Multiscale Convolution and Attention
Sensors · 23.02.2026 · 26 (4) · 1399
DOI: 10.3390/s26041399 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 23.02.2026. Verfasst von Mengdi Hou und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information and Artificial Intelligence, Wuzhou University, Wuzhou 543000, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Guangxi Science and Technology Plan, Wuzhou University Research Project.
Abstract (Originalsprache)
The Controller Area Network (CAN) protocol lacks native authentication mechanisms, exposing modern vehicles to critical security threats. While deep learning-based intrusion detection systems show promise, existing solutions require computational resources far exceeding automotive-grade microcontroller constraints, hindering practical embedded deployment. This paper proposes LCSMC-Net, an ultra-lightweight neural architecture for resource-constrained CAN intrusion detection. The framework integrates three innovations: (1) Separable Multiscale Convolution Lite (SMC-Lite) blocks capturing multitemporal attack patterns with minimal parameters; (2) Lightweight Channel-Temporal Attention (LCTA) achieving linear O(N) complexity through adaptive pruning; and (3) 6-dimensional CAN-optimized features exploiting protocol-specific characteristics for aggressive compression. The framework employs Bayesian hyperparameter optimization and knowledge distillation for systematic model compression. Extensive experiments on CAN and CAN-FD datasets demonstrate that LCSMC-Net achieves 99.89% accuracy with only 9401 parameters and 2.84M FLOPs, outperforming existing solutions while meeting real-time constraints of automotive embedded systems, providing a viable edge AI deployment solution.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronic Information and Artificial Intelligence, Wuzhou University, Wuzhou 543000, China.
- Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin 541004, China.
- School of Computer Application, Guilin University of Technology, Guilin 541004, China.
Förderung
- Key Research and Development Program of Guangxi Science and Technology Plan
- Wuzhou University Research Project
Zitieren
APA
Hou, M., Lan, B., Tang, C., & Huang, J. (2026). LCSMC-Net: Lightweight CAN Intrusion Detection via Separable Multiscale Convolution and Attention. Sensors, 26(4), 1399. https://doi.org/10.3390/s26041399
Vancouver
Hou M, Lan B, Tang C, Huang J. LCSMC-Net: Lightweight CAN Intrusion Detection via Separable Multiscale Convolution and Attention. Sensors. 2026;26(4):1399. doi:10.3390/s26041399
BibTeX
@article{Hou2026,
author = {Hou, Mengdi and Lan, Bitie and Tang, Chenghua and Huang, Jianbo},
title = {LCSMC-Net: Lightweight CAN Intrusion Detection via Separable Multiscale Convolution and Attention},
journal = {Sensors},
year = {2026},
volume = {26},
number = {4},
pages = {1399},
doi = {10.3390/s26041399}
}
EUVIMED