Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Network application identification method based on multilayer neural network

A multi-layer neural network and network application technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as low recognition efficiency, complex network structure, inability to identify and change network application types, etc., and achieve traffic speed. Fast, overcome the effect of complex structure

Inactive Publication Date: 2019-06-28
XIDIAN UNIV
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that a deep convolutional neural network is used to detect the load information of the entire data packet, the network structure is complex, and the recognition efficiency is low
The disadvantage of this method is that this method only generates feature values ​​by extracting the packet header information of the network data flow, so it cannot identify the type of network application that changes the encrypted traffic of the packet header information

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Network application identification method based on multilayer neural network
  • Network application identification method based on multilayer neural network
  • Network application identification method based on multilayer neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Refer to attached figure 1 , the specific steps of the implementation of the present invention will be further described.

[0038] Step 1, capture network traffic data packets.

[0039] Use a network sniffing tool to capture a section of network traffic in a wired network environment and a wireless network environment during peak hours of network traffic, and form data packets in the network traffic into a data packet set.

[0040] Step 2, generating a feature set of network data streams.

[0041] Divide the data packets with the same attribute in the data packet collection into a small collection, as a network data flow, repeat the selection until all the data in the data packet collection are divided, and finally obtain a network data flow collection composed of multiple network data flows .

[0042] The same attributes in the data packet set include five types: source IP address of the data packet, source port of the data packet, destination IP address of the data...

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

No PUM Login to View More

Abstract

The invention discloses a network application identification method based on a multilayer neural network, and the method achieves the training of the neural network through extracting data flow features, and solves the problems that the encrypted flow cannot be identified, and the identification efficiency is low in the prior art. The method comprises the following steps of: 1, capturing a networkflow data packet; 2, generating a feature set of the network data flow; 3, generating a data set; 4, generating a training set and a test set; 5, constructing a multilayer neural network; 6, traininga neural network; And 7, identifying the test sample set. The method has the advantages of capability of identifying the encrypted traffic, simple model and high identification speed, and can be usedfor identifying the network application type of the network traffic.

Description

technical field [0001] The invention belongs to the technical field of communication, and further relates to a network application identification method based on a multi-layer neural network in the technical field of network traffic identification. The present invention is used to identify the network application type of the network flow by acquiring the information of the network flow. Background technique [0002] Network application identification technology refers to identifying the network application to which the network traffic belongs by obtaining certain information of network traffic, also known as network traffic identification technology. Network application identification can not only optimize network configuration and reduce network security risks, but also provide better service quality based on user behavior analysis. Existing network application identification methods are mainly divided into four types: port-based network application identification, deep pa...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/26G06N3/04G06N3/08
Inventor 张岗山张至权赵林靖刘炯冯磊吴炜
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com