EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Diffusion Model Based on Network Intrusion Detection Method for Industrial Cyber-Physical Systems

Bin Tang, Yan Lu, Qi Li, Yueying Bai, Jie Yu, Xu Yu

Sensors · 19.01.2023 · 23 (3) · 1141

DOI: 10.3390/s23031141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.01.2023. Verfasst von Bin Tang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Qingdao Innovation and Development Base, Harbin Engineering University, Qingdao 266000, China. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, the Fundamental Research Funds for the Central Universities, JLU.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industrial Cyber-Physical Systems (ICPS) connect intelligent manufacturing equipment equipped with sensors, wireless and RFID communication technologies through data interaction, which makes the interior of the factory, even between factories, become a whole. However, intelligent factories will suffer information leakage and equipment damage when being attacked by ICPS intrusion. Therefore, the network security of ICPS cannot be ignored, and researchers have conducted in-depth research on network intrusion detection for ICPS. Though machine learning and deep learning methods are often used for network intrusion detection, the problem of data imbalance can cause the model to pay attention to the misclassification cost of the prevalent class, but ignore that of the rare class, which seriously affects the classification performance of network intrusion detection models. Considering the powerful generative power of the diffusion model, we propose an ICPS Intrusion Detection system based on the Diffusion model (IDD). Firstly, data corresponding to the rare class is generated by the diffusion model, which makes the training dataset of different classes balanced. Then, the improved BiLSTM classification network is trained on the balanced training set. Extensive experiments are conducted to show that the IDD method outperforms the existing baseline method on several available datasets.

Schlagwörter

Stichwörter der Autor:innen

BiLSTMICPSdiffusion modelimbalanced dataintrusion detection

Autor:innen und Institutionen

  • Qingdao Innovation and Development Base, Harbin Engineering University, Qingdao 266000, China.
  • Ship Science and Technology Co., Ltd., Harbin Engineering University, Qingdao 266000, China.
  • College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266000, China.
  • Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130000, China.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province
  • the Fundamental Research Funds for the Central Universities, JLU
  • Fundamental Research Funds for the Central Universities, JLU

Zitieren

APA

Tang, B., Lu, Y., Li, Q., Bai, Y., Yu, J., & Yu, X. (2023). A Diffusion Model Based on Network Intrusion Detection Method for Industrial Cyber-Physical Systems. Sensors, 23(3), 1141. https://doi.org/10.3390/s23031141

Vancouver

Tang B, Lu Y, Li Q, Bai Y, Yu J, Yu X. A Diffusion Model Based on Network Intrusion Detection Method for Industrial Cyber-Physical Systems. Sensors. 2023;23(3):1141. doi:10.3390/s23031141

BibTeX
@article{Tang2023,
  author = {Tang, Bin and Lu, Yan and Li, Qi and Bai, Yueying and Yu, Jie and Yu, Xu},
  title = {A Diffusion Model Based on Network Intrusion Detection Method for Industrial Cyber-Physical Systems},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {3},
  pages = {1141},
  doi = {10.3390/s23031141}
}
Kostenlos starten →