期刊
IEEE WIRELESS COMMUNICATIONS LETTERS
卷 10, 期 8, 页码 1707-1711出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LWC.2021.3077946
关键词
Feature extraction; Wireless sensor networks; Training; Computational modeling; Performance evaluation; Deep learning; Artificial neural networks; Wireless sensor networks; intrusion detection; deep learning; autoencoder; lightweight neural network
资金
- Cyber Security from the National Key Research and Development Program of Shanghai Jiao Tong University [2019QY0703]
- Ministry of Industry and Information Technology of China [TC190A3WZ2]
- Summit of the Six Top Talents Program of Jiangsu [XYDXX-010]
- Program for High-Level Entrepreneurial and Innovative Team [CZ002SC19001]
- Open Project Program of the State Key Laboratory of CAD&CG of Zhejiang University [A2102]
- Key Laboratory of Universal Wireless Communications (BUPT) of Ministry of Education of China [KFKT-2020106]
The rapid growth of wireless sensor networks and applications has led to an increase in unsolicited intrusions and security threats, disrupting normal operations. Deep learning-based network intrusion detection methods have been widely studied, but their high computational complexity hinders deployment in devices with limited processing power. This letter introduces a lightweight dynamic autoencoder network (LDAN) for NID, which efficiently extracts features through a lightweight structure design. Experimental results demonstrate that the proposed model achieves high accuracy and robustness while significantly reducing computational cost and model size.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据