EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Network Intrusion Detection Model Based on BiLSTM with Multi-Head Attention Mechanism

Jingqi Zhang, Xin Zhang, Zhaojun Liu, Fa Fu, Yihan Jiao, Fei Xu

Electronics · 08.10.2023 · 12 (19) · 4170

DOI: 10.3390/electronics12194170 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 08.10.2023. Verfasst von Jingqi Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 74-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hainan Province Science and Technology Special Fund, Haikou Science and Technology Plan Project, Key Laboratory of PK System Technologies Research of Hainan, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A network intrusion detection tool can identify and detect potential malicious activities or attacks by monitoring network traffic and system logs. The data within intrusion detection networks possesses characteristics that include a high degree of feature dimension and an unbalanced distribution across categories. Currently, the actual detection accuracy of some detection models is relatively low. To solve these problems, we propose a network intrusion detection model based on multi-head attention and BiLSTM (Bidirectional Long Short-Term Memory), which can introduce different attention weights for each vector in the feature vector that strengthen the relationship between some vectors and the detection attack type. The model also utilizes the advantage that BiLSTM can capture long-distance dependency relationships to obtain a higher detection accuracy. This model combined the advantages of the two models, adding a dropout layer between the two models to improve the detection accuracy while preventing training overfitting. Through experimental analysis, the network intrusion detection model that utilizes multi-head attention and BilSTM achieved an accuracy of 98.29%, 95.19%, and 99.08% on the KDDCUP99, NSLKDD, and CICIDS2017 datasets, respectively.

Förderung

  • Hainan Province Science and Technology Special Fund
  • Haikou Science and Technology Plan Project
  • Key Laboratory of PK System Technologies Research of Hainan, China

Zitieren

APA

Zhang, J., Zhang, X., Liu, Z., Fu, F., Jiao, Y., & Xu, F. (2023). A Network Intrusion Detection Model Based on BiLSTM with Multi-Head Attention Mechanism. Electronics, 12(19), 4170. https://doi.org/10.3390/electronics12194170

Vancouver

Zhang J, Zhang X, Liu Z, Fu F, Jiao Y, Xu F. A Network Intrusion Detection Model Based on BiLSTM with Multi-Head Attention Mechanism. Electronics. 2023;12(19):4170. doi:10.3390/electronics12194170

BibTeX
@article{Zhang2023,
  author = {Zhang, Jingqi and Zhang, Xin and Liu, Zhaojun and Fu, Fa and Jiao, Yihan and Xu, Fei},
  title = {A Network Intrusion Detection Model Based on BiLSTM with Multi-Head Attention Mechanism},
  journal = {Electronics},
  year = {2023},
  volume = {12},
  number = {19},
  pages = {4170},
  doi = {10.3390/electronics12194170}
}
Kostenlos starten →