EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Deep Learning-Based Feature Selection and Intrusion Detection Method on the Internet of Things

Xuejiao Chen iD, Minyao Liu iD, Zixuan Wang iD, Yun Wang iD

Sensors · 12.08.2024 · 24 (16) · 5223

DOI: 10.3390/s24165223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.08.2024. Verfasst von Xuejiao Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Communications, Nanjing Vocational College of Information Technology, Nanjing 210023, China. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Suzhou Fundamental Research Project, China Suzhou Innovative Association Project Grant, Suzhou Fundamental Research Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid advancement of the Internet of Things, network security has garnered increasing attention from researchers. Applying deep learning (DL) has significantly enhanced the performance of Network Intrusion Detection Systems (NIDSs). However, due to its complexity and “black box” problem, deploying DL-based NIDS models in practical scenarios poses several challenges, including model interpretability and being lightweight. Feature selection (FS) in DL models plays a crucial role in minimizing model parameters and decreasing computational overheads while enhancing NIDS performance. Hence, selecting effective features remains a pivotal concern for NIDSs. In light of this, this paper proposes an interpretable feature selection method for encrypted traffic intrusion detection based on SHAP and causality principles. This approach utilizes the results of model interpretation for feature selection to reduce feature count while ensuring model reliability. We evaluate and validate our proposed method on two public network traffic datasets, CICIDS2017 and NSL-KDD, employing both a CNN and a random forest (RF). Experimental results demonstrate superior performance achieved by our proposed method.

Schlagwörter

Stichwörter der Autor:innen

RFESHAPconvolutional neural networkdeep learningfeature selectioninformation gainmodel interpretabilityrandom forest

Autor:innen und Institutionen

  • School of Communications, Nanjing Vocational College of Information Technology, Nanjing 210023, China.
  • School of Modern Posts, Nanjing University of Posts & Telecommunications, Nanjing 210003, China.

ORCID-Profile: Xuejiao Chen, Minyao Liu, Zixuan Wang, Yun Wang

Förderung

  • China Suzhou Fundamental Research Project
  • China Suzhou Innovative Association Project Grant
  • Suzhou Fundamental Research Project
  • Suzhou Innovative Association Project

Zitieren

APA

Chen, X., Liu, M., Wang, Z., & Wang, Y. (2024). Explainable Deep Learning-Based Feature Selection and Intrusion Detection Method on the Internet of Things. Sensors, 24(16), 5223. https://doi.org/10.3390/s24165223

Vancouver

Chen X, Liu M, Wang Z, Wang Y. Explainable Deep Learning-Based Feature Selection and Intrusion Detection Method on the Internet of Things. Sensors. 2024;24(16):5223. doi:10.3390/s24165223

BibTeX
@article{Chen2024,
  author = {Chen, Xuejiao and Liu, Minyao and Wang, Zixuan and Wang, Yun},
  title = {Explainable Deep Learning-Based Feature Selection and Intrusion Detection Method on the Internet of Things},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {16},
  pages = {5223},
  doi = {10.3390/s24165223}
}
Kostenlos starten →