Real-Time Intrusion Detection in Wireless Network: A Deep Learning-Based Intelligent Mechanism

Liqun Yang,Liang Yin,Zhoujun Li,Jianqiang Li,Yufei Zhao,Zhonghao Sun

doi:10.1109/access.2020.3019973

Abstract

With the development of the wireless network techniques, the number of cyber-attack increases significantly, which has seriously threat the security of Wireless Local Area Network (WLAN). The traditional intrusion detection technology is a prevalent area of study for numerous years, but it may not have a good detection performance in a real-time way. Therefore, it is urgent to design a detection mechanism to detect the attacks timely. In this paper, we exploit a CDBN (Conditional Deep Belief Network)-based intrusion detection mechanism to recognize the attack features and perform the wireless network intrusion detection in real time. To avoid the impact of the imbalanced dataset and the data redundancy on the detection accuracy, a window-based instance selection algorithm “SamSelect” is adopted to undersample the majority class data samples, and a Stacked Contractive Auto-Encoder (SCAE) algorithm is proposed to reduce the dimension of the data samples. By doing so, our proposed mechanism can effectively detect the potential attack and achieve high accuracy. The experiment results show that CDBN can be effectively combined with “SamSelect” and SCAE, and the proposed mechanism has a high detection speed and accuracy, with the average detection time 1.14 ms and the detection accuracy 0.974.

Highlights

With the extensive popularization of Wireless Local Area Networks (WLAN) technology used in hardware devices, the IEEE 802.11 protocol based short-distance transmission wireless network is facing great security challenges [1]
We use Stacked Contractive Auto-encoder (SCAE) algorithm to eliminate the redundancy of experimental data
We illustrate our work by four cases, and the first two cases show that Stacked Contractive Auto-Encoder (SCAE) is feasible to reduce the dimensionality with the average reconstruction error 0.058

Summary

INTRODUCTION

With the extensive popularization of Wireless Local Area Networks (WLAN) technology used in hardware devices, the IEEE 802.11 protocol based short-distance transmission wireless network is facing great security challenges [1]. To eliminate the impact of the data redundancy on intrusion detection performance, the dimension reduction methods such as principal component analysis (PCA), linear discriminant analysis (LDA), independent component analysis (ICA) and their variants have been adopted for dimensionality reduction in different research areas [19], [20]. These methods are linear and have good effects when the data is linear structure and Gaussian distribution. These methods need to synthesize the minority-class samples, and this will lead to the minority-class samples tend to overlap with the majorityclass samples [29]

MOTIVATION AND CONTRIBUTIONS

THE FINE-TUNING PROCESS OF CDBN

THE FEASIBILITY ANALYSIS OF SCAE ON DIMENSIONALITY REDUCTION

Findings

CONCLUSION AND FUTURE WORK