EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Attack Intrusion Detection for In-Vehicle CAN-FD Messages

Fei Gao iD, Jinshuo Liu iD, Yingqi Liu, Zhenhai Gao, Rui Zhao iD

Sensors · 27.05.2024 · 24 (11) · 3461

DOI: 10.3390/s24113461 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.05.2024. Verfasst von Fei Gao und 4 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130025, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As an enhanced version of standard CAN, the Controller Area Network with Flexible Data (CAN-FD) rate is vulnerable to attacks due to its lack of information security measures. However, although anomaly detection is an effective method to prevent attacks, the accuracy of detection needs further improvement. In this paper, we propose a novel intrusion detection model for the CAN-FD bus, comprising two sub-models: Anomaly Data Detection Model (ADDM) for spotting anomalies and Anomaly Classification Detection Model (ACDM) for identifying and classifying anomaly types. ADDM employs Long Short-Term Memory (LSTM) layers to capture the long-range dependencies and temporal patterns within CAN-FD frame data, thus identifying frames that deviate from established norms. ACDM is enhanced with the attention mechanism that weights LSTM outputs, further improving the identification of sequence-based relationships and facilitating multi-attack classification. The method is evaluated on two datasets: a real-vehicle dataset including frames designed by us based on known attack patterns, and the CAN-FD Intrusion Dataset, developed by the Hacking and Countermeasure Research Lab. Our method offers broader applicability and more refined classification in anomaly detection. Compared with existing advanced LSTM-based and CNN-LSTM-based methods, our method exhibits superior performance in detection, achieving an improvement in accuracy of 1.44% and 1.01%, respectively.

Schlagwörter

Stichwörter der Autor:innen

CAN-FDLSTManomaly detectionattention mechanismdeep learningvehicle security

Autor:innen und Institutionen

  • State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130025, China.
  • College of Automotive Engineering, Jilin University, Changchun 130025, China.
  • Strategic Cooperation Department, Mobje Co., Ltd., Changchun 130013, China.

ORCID-Profile: Fei Gao, Jinshuo Liu, Rui Zhao

Förderung

  • National Science Foundation of China

Zitieren

APA

Gao, F., Liu, J., Liu, Y., Gao, Z., & Zhao, R. (2024). Multi-Attack Intrusion Detection for In-Vehicle CAN-FD Messages. Sensors, 24(11), 3461. https://doi.org/10.3390/s24113461

Vancouver

Gao F, Liu J, Liu Y, Gao Z, Zhao R. Multi-Attack Intrusion Detection for In-Vehicle CAN-FD Messages. Sensors. 2024;24(11):3461. doi:10.3390/s24113461

BibTeX
@article{Gao2024,
  author = {Gao, Fei and Liu, Jinshuo and Liu, Yingqi and Gao, Zhenhai and Zhao, Rui},
  title = {Multi-Attack Intrusion Detection for In-Vehicle CAN-FD Messages},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {11},
  pages = {3461},
  doi = {10.3390/s24113461}
}
Kostenlos starten →