Communication Protocol Classification Based on LSTM and DBN

Wenwen Li,Zheng Dou,Lin Qi

doi:10.1109/access.2020.2979768

Wenwen Li, Zheng Dou + Show 1 more

Open Access

https://doi.org/10.1109/access.2020.2979768

Copy DOI

Abstract

In the battlefield, we often don't know the parameters about enemy wireless communication system. Therefore, we need to use electronic reconnaissance equipment to search, intercept, identify and analyze enemy wireless communication signal. However, the exciting electronic reconnaissance methods can only detect signal layer parameters such as signal carrier frequency and bandwidth, and cannot obtain more information. In order to improve the reconnaissance ability, we propose a novel communication protocol classification algorithm based on long short-term memory (LSTM) and deep belief network (DBN). We first introduce the DBN, then simulates communication protocol classification method based on DBN. In order to improve the performance, we optimize the method. We uses the LSTM to pre-process the data to extract the feature firstly. Then we make the feature as the input of DBN to classify the communication protocol. Finally we make simulation to verify the effectiveness of the proposed algorithm. Simulation results show that the proposed algorithm has very good performance to classify the communication protocol.

Highlights

Nowadays, more and more countries have increasingly attached importance to electronic countermeasure system
The existing communication protocol classification methods first identify the modulation scheme, frequency and other signal parameters, vectorize the parameters according to the entropy, and compare the parameter set with the protocol parameters or use the machine learning method to classify the protocol
In order to improve the communication protocol classification accuracy, we propose a novel communication protocol classification algorithm based on long short-term memory (LSTM) and deep belief network (DBN)

Summary

INTRODUCTION

More and more countries have increasingly attached importance to electronic countermeasure system. The simulation results show that the proposed method can identify network tunneling protocols with high accuracy and low processing cost. The existing communication protocol classification methods first identify the modulation scheme, frequency and other signal parameters, vectorize the parameters according to the entropy, and compare the parameter set with the protocol parameters or use the machine learning method to classify the protocol. This method depends on the identification of various signal parameters.

BACKGROUND

EVALUATION INDEX

Findings

CONCLUSION