Research On Classification And Identification Of Network Encrypted Traffic Under Wireless Transmission Condition

In the case of relatively developed networks,with the improvement of domestic and foreign network security laws and regulations and the rise of user awareness of network security,the encryption of network traffic has become an inevitable trend.As an important part of edge network communication in today's network environment,wireless communication has been widely used in various fields.Its main research focuses on wireless communication network encryption technology,wireless network measurement technology and non-network environment-related encrypted flow identification technology.This paper studies the characteristics of encrypted traffic in wireless communication networks.By selecting effective features and using classification algorithms,it solves the problem of feature measurement and identification when only one-way traffic and easy-to-occur data packets are missing under wireless transmission,and complete the wireless communication Network encryption flow classification and identification,to achieve effective supervision of wireless networks.This paper is oriented to the needs of accurate identification of wireless communication data,constructs a wireless communication network encrypted stream transmission model,carries out research on scientific issues such as feature extraction of wireless communication network encrypted streams,feature classification methods,and proposes a new method of wireless communication service classification and identification.The main research contents of this paper are as follows:1.In view of the wide variety and large differences of wireless communication system protocols,construct a wireless network transmission environment,and collect data in this environment for follow-up experiments.2.The encrypted traffic collected by the wireless communication network is often one-way and does not have the problem of interactive information,extract the multi-level characteristics of the encrypted traffic,and establish a more general feature set for wireless communication encryption services.3.Multi-level classification is performed on the feature set obtained from the collected encrypted traffic,and the characteristics of each business are classified,so as to achieve the purpose of classification and identification of wireless network encrypted traffic.This paper makes innovations in the implementation of multi-level protocol encryption extraction and analysis methods,and solves the problem of encryption service identification under the condition of one-way traffic and data loss.77 dimensional feature vectors at different levels are established.Through algorithms such as random forest,the accuracy of wireless network encryption rvice identification is 96.3%,good recognition effect is obtained.