Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection
Sensors · 22.06.2026 · 26 (12) · 3964
DOI: 10.3390/s26123964 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.06.2026. Verfasst von Jonggwon Kim und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Intelligent Semiconductors, Soongsil University, Seoul 06978, Republic of Korea. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Evaluation Institute of Industrial Technology 647 (KEIT), the Korea Institute for Advancement of Technology (KIAT), and the Institute of Information 648….
Abstract (Originalsprache)
Modern connected vehicles rely on the controller area network (CAN) to disseminate safety-critical in-vehicle information, including sensor-related and vehicle-state signals such as engine revolutions per minute (RPM) and gear state, among electronic control units (ECUs). Because CANs lack built-in authentication and encryption, malicious message injection and spoofing can compromise the integrity and availability of vehicular sensing and control functions. Existing deep-learning-based intrusion-detection systems (IDSs) show a clear trade-off: supervised methods perform well on known attacks but rely on costly labels, whereas unsupervised methods can identify unseen attacks but often suffer from high false-positive rates. To address these limitations, this paper proposes a semi-supervised generative adversarial network (SGAN) framework for CAN bus intrusion detection that combines image-based CAN representation with adversarial learning. Consecutive CAN messages are converted into 64×9 grayscale images, and the proposed framework is trained in three phases. First, the discriminator establishes an initial decision boundary using a small labeled subset. It then refines this boundary through distribution-level likelihood objectives and generated samples. Finally, the generator is trained to produce realistic samples capable of deceiving the discriminator. The proposed method was evaluated on the Hacking and Countermeasure Research Lab (HCRL) car-hacking dataset using leave-one-class-out experiments to simulate unknown attacks and achieved an average accuracy of 99.73% and an average F1-score of 99.63% on unknown attacks. Moreover, with only 0.21 M parameters and 3.25 M floating-point operations (FLOPs), the model is well suited for resource-constrained in-vehicle platforms. These results indicate that the proposed framework can serve as a practical cybersecurity component for protecting CAN-carried data in vehicular sensing applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Intelligent Semiconductors, Soongsil University, Seoul 06978, Republic of Korea.
ORCID-Profile: Jonggwon Kim, Hyungchul Im, Semin Kim, Seongsoo Lee
Förderung
- Korea Evaluation Institute of Industrial Technology 647 (KEIT), the Korea Institute for Advancement of Technology (KIAT), and the Institute of Information 648…
Zitieren
APA
Kim, J., Im, H., Kim, S., & Lee, S. (2026). Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection. Sensors, 26(12), 3964. https://doi.org/10.3390/s26123964
Vancouver
Kim J, Im H, Kim S, Lee S. Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection. Sensors. 2026;26(12):3964. doi:10.3390/s26123964
BibTeX
@article{Kim2026,
author = {Kim, Jonggwon and Im, Hyungchul and Kim, Semin and Lee, Seongsoo},
title = {Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {12},
pages = {3964},
doi = {10.3390/s26123964}
}
EUVIMED