A lightweight intrusion detection method for IoT based on deep learning and dynamic quantization
PeerJ Computer Science · 22.09.2023 · 9 · e1569
DOI: 10.7717/peerj-cs.1569 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 22.09.2023. Verfasst von Zhendong Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China. Die Arbeit wurde bisher 148-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Natural Science Foundation of China, The Natural Science Foundation of Jiangxi Province.
Abstract (Originalsprache)
Intrusion detection ensures that IoT can protect itself against malicious intrusions in extensive and intricate network traffic data. In recent years, deep learning has been extensively and effectively employed in IoT intrusion detection. However, the limited computing power and storage space of IoT devices restrict the feasibility of deploying resource-intensive intrusion detection systems on them. This article introduces the DL-BiLSTM lightweight IoT intrusion detection model. By combining deep neural networks (DNNs) and bidirectional long short-term memory networks (BiLSTMs), the model enables nonlinear and bidirectional long-distance feature extraction of complex network information. This capability allows the system to capture complex patterns and behaviors related to cyber-attacks, thus enhancing detection performance. To address the resource constraints of IoT devices, the model utilizes the incremental principal component analysis (IPCA) algorithm for feature dimensionality reduction. Additionally, dynamic quantization is employed to trim the specified cell structure of the model, thereby reducing the computational burden on IoT devices while preserving accurate detection capability. The experimental results on the benchmark datasets CIC IDS2017, N-BaIoT, and CICIoT2023 demonstrate that DL-BiLSTM surpasses traditional deep learning models and cutting-edge detection techniques in terms of detection performance, while maintaining a lower model complexity.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China.
- School of Electrical Engineering ang Automation, Jiangxi University of Science and Technology, Ganzhou, China.
Förderung
- The Natural Science Foundation of China
- The Natural Science Foundation of Jiangxi Province
Zitieren
APA
Wang, Z., Chen, H., Yang, S., Luo, X., Li, D., & Wang, J. (2023). A lightweight intrusion detection method for IoT based on deep learning and dynamic quantization. PeerJ Computer Science, 9, e1569. https://doi.org/10.7717/peerj-cs.1569
Vancouver
Wang Z, Chen H, Yang S, Luo X, Li D, Wang J. A lightweight intrusion detection method for IoT based on deep learning and dynamic quantization. PeerJ Computer Science. 2023;9:e1569. doi:10.7717/peerj-cs.1569
BibTeX
@article{Wang2023,
author = {Wang, Zhendong and Chen, Hui and Yang, Shuxin and Luo, Xiao and Li, Dahai and Wang, Junling},
title = {A lightweight intrusion detection method for IoT based on deep learning and dynamic quantization},
journal = {PeerJ Computer Science},
year = {2023},
volume = {9},
pages = {e1569},
doi = {10.7717/peerj-cs.1569}
}
EUVIMED