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

Abnormal traffic detection system and method based on hybrid convolutional neural network

A convolutional neural network and abnormal traffic technology, applied in the field of computer network security, can solve the problems of obtaining deep features and low accuracy, and achieve the effect of reasonable design, improved accuracy and precision, and effective network intrusion detection

Inactive Publication Date: 2021-07-13
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods cannot obtain deep features from network streams, so the accuracy is low

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
  • Abnormal traffic detection system and method based on hybrid convolutional neural network
  • Abnormal traffic detection system and method based on hybrid convolutional neural network
  • Abnormal traffic detection system and method based on hybrid convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] This embodiment uses the UNSW_NB15 data set for simulation experiments. In the detection classification experiment, the use of different ratios of data sets as training sets, compared experimental results under different data ratios. The effects of this embodiment to solve an abnormal flow detection problem with the existing abnormal flow detection method, and see Table 1 for specific results.

[0054] Table 1 shows the results of the test

[0055]

[0056] According to Table 1, when the training set ratio is 80%, the method accuracy and detection rate of the present embodiment are both highest, the error rate is the lowest; when the training set ratio is 70%, the method of the method is the highest. The error rate is the lowest; when the training set ratio is 60%, the method of the method of the present embodiment is the highest, the error is the lowest, and regardless of the training set proportion, the method of the present embodiment is used. All are the highest, the ...

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 an abnormal traffic detection system based on a hybrid convolutional neural network. The abnormal traffic detection system comprises a network traffic data capture module, a data processing module, a core model analysis module and an abnormal response module. The invention also discloses an abnormal traffic detection method based on the hybrid convolutional neural network, and the method comprises the steps: firstly collecting the network traffic data, and carrying out the data preprocessing with the network flow as an object; then, respectively learning sparsity features of the one-dimensional network traffic data and spatial features in the two-dimensional network traffic data through a convolutional neural network; inputting the feature information into an attention mechanism network to further learn key features; and finally outputting a detection result. According to the method, the key characteristics of the network traffic can be well extracted, and the accuracy and the precision rate of the detection model are improved. The method is reasonable in design and can be used as an effective method for realizing network intrusion detection.

Description

Technical field [0001] The present invention belongs to the field of computer network security technology, and more particularly to an abnormal flow detection system and method based on a mixed convolutional neural network. Background technique [0002] The high-speed development of Internet and network communication technology has brought great changes to people's lives and production. While enjoying the convenience of the network, network security issues have become increasingly serious, and the network's abnormal traffic has a large impact on network availability, and may even lead to unable to access the Internet. [0003] The Internet is easily subject to many potential network attacks, accurately detecting abnormal traffic is especially important for the security and reliability of the network. The reason for the abnormality of network traffic is mainly referred to whether the network topology is unreasonable or unworthy from user operation. It mainly refers to an abnormal ...

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
IPC IPC(8): H04L29/06G06N3/04G06N3/08
CPCH04L63/1425H04L63/1416G06N3/08G06N3/045
Inventor 李晋国丁朋鹏温蜜周绍景崔星
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
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