An Efficient Intrusion Detection Method Based on Dynamic Autoencoder

Ruijie Zhao, Jie Yin, Zhi Xue, Guan Gui, Bamidele Adebisi, Tomoaki Ohtsuki, Haris Gacanin, Hikmet Sari

研究成果: Article査読

2 被引用数 (Scopus)

抄録

The proliferation of wireless sensor networks (WSNs) and their applications has attracted remarkable growth in unsolicited intrusions and security threats, which disrupt the normal operations of the WSNs. Deep learning (DL)-based network intrusion detection (NID) methods have been widely investigated and developed. However, the high computational complexity of DL seriously hinders the actual deployment of the DL-based model, particularly in the devices of WSNs that do not have powerful processing performance due to power limitation. In this letter, we propose a lightweight dynamic autoencoder network (LDAN) method for NID, which realizes efficient feature extraction through lightweight structure design. Experimental results show that our proposed model achieves high accuracy and robustness while greatly reducing computational cost and model size.

本文言語English
論文番号9424716
ページ(範囲)1707-1711
ページ数5
ジャーナルIEEE Wireless Communications Letters
10
8
DOI
出版ステータスPublished - 2021 8

ASJC Scopus subject areas

  • 制御およびシステム工学
  • 電子工学および電気工学

フィンガープリント

「An Efficient Intrusion Detection Method Based on Dynamic Autoencoder」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル