A Lightweight Intrusion Detection System with Dynamic Feature Fusion Federated Learning for Vehicular Network Security
Sensors · 25.07.2025 · 25 (15) · 4622
DOI: 10.3390/s25154622 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 25.07.2025. Verfasst von Junjun Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of China Regional Joint Innovation Key Project, Henan Provincial Natural Science Foundation-Excellent Young Innovation Group Project.
Abstract (Originalsprache)
The rapid integration of complex sensors and electronic control units (ECUs) in autonomous vehicles significantly increases cybersecurity risks in vehicular networks. Although the Controller Area Network (CAN) is efficient, it lacks inherent security mechanisms and is vulnerable to various network attacks. The traditional Intrusion Detection System (IDS) makes it difficult to effectively deal with the dynamics and complexity of emerging threats. To solve these problems, a lightweight vehicular network intrusion detection framework based on Dynamic Feature Fusion Federated Learning (DFF-FL) is proposed. The proposed framework employs a two-stream architecture, including a transformer-augmented autoencoder for abstract feature extraction and a lightweight CNN-LSTM–Attention model for preserving temporal and local patterns. Compared with the traditional theoretical framework of the federated learning, DFF-FL first dynamically fuses the deep feature representation of each node through the transformer attention module to realize the fine-grained cross-node feature interaction in a heterogeneous data environment, thereby eliminating the performance degradation caused by the difference in feature distribution. Secondly, based on the final loss LAEX,X^ index of each node, an adaptive weight adjustment mechanism is used to make the nodes with excellent performance dominate the global model update, which significantly improves robustness against complex attacks. Experimental evaluation on the CAN-Hacking dataset shows that the proposed intrusion detection system achieves more than 99% F1 score with only 1.11 MB of memory and 81,863 trainable parameters, while maintaining low computational overheads and ensuring data privacy, which is very suitable for edge device deployment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China.
- Longmen Laboratory, Luoyang 471000, China.
- State Key Laboratory of Intelligent Agricultural Power Equipment, Luoyang 471000, China.
ORCID-Profile: Tingting Xu
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of China Regional Joint Innovation Key Project
- Henan Provincial Natural Science Foundation-Excellent Young Innovation Group Project
Zitieren
APA
Li, J., Ma, Y., Bai, J., Chen, C., Xu, T., & Ding, C. (2025). A Lightweight Intrusion Detection System with Dynamic Feature Fusion Federated Learning for Vehicular Network Security. Sensors, 25(15), 4622. https://doi.org/10.3390/s25154622
Vancouver
Li J, Ma Y, Bai J, Chen C, Xu T, Ding C. A Lightweight Intrusion Detection System with Dynamic Feature Fusion Federated Learning for Vehicular Network Security. Sensors. 2025;25(15):4622. doi:10.3390/s25154622
BibTeX
@article{Li2025,
author = {Li, Junjun and Ma, Yanyan and Bai, Jiahui and Chen, Congming and Xu, Tingting and Ding, Chi},
title = {A Lightweight Intrusion Detection System with Dynamic Feature Fusion Federated Learning for Vehicular Network Security},
journal = {Sensors},
year = {2025},
volume = {25},
number = {15},
pages = {4622},
doi = {10.3390/s25154622}
}
EUVIMED