Unknown wireless network protocol feature extraction method based on sequence association

Abstract

Aiming at the problem of low accuracy and long time consumption of feature extraction in the process of unknown protocol identification, a feature extraction method based on sequence association is proposed. By analyzing the extracted feature sequences and their positional relationships, this method can obtain the connection between feature sequences, which can be used as protocol features. At the same time, aiming at the problem of high time consumption of existing feature extraction methods, extra rules are made for the above analysis process, and the feature extraction process is divided into two parts: intra-frame feature extraction and inter-frame feature extraction. By analyzing the position constraints in the process, we can reduce the time consumption and improve the accuracy of feature extraction. Simulation results show that this method can reduce time consumption and improve the accuracy of unknown wireless network protocol feature extraction.