Application traffic identification method under VPN based on random forest of distribution characteristics
A technology based on random forest algorithm and distribution features, which is applied in the field of application traffic identification under Shadowsocks VPN based on distribution features and random forest algorithm, can solve the problem of low accuracy rate of application program traffic, improve identification accuracy and improve efficiency Effect
Active Publication Date: 2022-03-04
XIDIAN UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The purpose of the present invention is to overcome the deficiencies in the above-mentioned prior art, and proposes a method for identifying application traffic under Shadowsocks VPN based on distribution characteristics and random forest algorithm, which is used to solve the application of prior art in identifying Shadowsocks VPN A technical problem with low accuracy in program flow
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0043] Below in conjunction with accompanying drawing and specific embodiment, the present invention is described in further detail:
[0044] refer to figure 1 , the present invention comprises the following steps:
[0045] Step 1) Obtain smart phone traffic data and preprocess the smart phone traffic data:
[0046] Step 1a) Turn on the hotspot on the computer with the wireless network card, connect the smartphone used in the experiment to the hotspot, firstly run Telegram, Facebook, YouTube, Whatsapp and Twitter respectively when Shadowsocks VPN is turned on, and then do not turn on Shadowsocks Run other applications in the case of VPN, use the Wireshark packet capture program on the computer to capture the smartphone traffic from the wireless network card, and save them in different pcap files according to the application, and add tags to these files according to the application name, which is convenient Add labels to the training set data later;
[0047] Step 1b) Compile...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention proposes a method for identifying application program traffic under a VPN based on a random forest of distribution characteristics, which is used to solve the technical problem of low accuracy in identifying application program traffic under the Shadowsocks VPN in the prior art. The implementation steps are as follows: Smartphone traffic data is preprocessed to obtain the time feature vector set, statistical feature vector set, and distribution feature vector set of the flow data set, and these sets are formed into a feature matrix to obtain training sets, Shadowsocks VPN training sets and test sets, based on random The forest algorithm obtains a binary classification model and a multi-classification model, and finally obtains the identification result of application traffic. The method adopted by the present invention to extract the distribution characteristics of flow data to form two training sets and input them into the random forest algorithm to obtain two classification models to identify the application flow under Shadowsocks VPN can significantly improve the accuracy of flow identification, and at the same time, due to the use of two A smaller model can improve the efficiency of the recognition method.
Description
technical field [0001] The invention belongs to the field of network technology, and relates to a method for identifying application program traffic under Shadowsocks VPN, in particular to a method for identifying application program traffic under Shadowsocks VPN based on distribution characteristics and a random forest algorithm. Background technique [0002] A virtual private network (Virtual Private Network, VPN) is a technology that establishes a private network on a public network to realize encrypted communication. Common VPNs are implemented based on the IPSec protocol. The VPN based on the IPSec protocol is divided into two parts, the client and the server. The client and the server first negotiate the key, and then the client encrypts the network layer payload of the data packet, encapsulates it, and adds a new network layer header. After that, the client and the server communicate through this encrypted data packet. This technology has been used by illegal network...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04L43/026H04L43/067H04L43/062H04W24/08G06K9/62
CPCH04L43/026H04L43/067H04L43/062H04W24/08G06F18/24323
Inventor 杨超王岁兴苏锐丹郑昱任秋凝马建峰郭刚刘丙楠
Owner XIDIAN UNIV