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

Abnormal flow detection method based on GBR image

A technology of abnormal flow and detection method, applied in image enhancement, image analysis, image data processing, etc., to reduce the amount of parameters, avoid huge calculations, and reduce the false alarm rate of detection

Active Publication Date: 2020-06-26
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem of abnormal traffic detection in the network, and proposes a method for detecting abnormal traffic based on GBR images

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 flow detection method based on GBR image
  • Abnormal flow detection method based on GBR image
  • Abnormal flow detection method based on GBR image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0049] Such as figure 1 As shown, the present invention provides a method for detecting abnormal traffic based on GBR images, which is characterized in that it comprises the following steps:

[0050] S1: Convert traffic data into visualized GBR images;

[0051] S2: Store the GBR image data in the distributed file system;

[0052] S3: Based on the distributed file system, the Apache Spark framework is used to train the sub-convolutional neural network model for each data block of the GBR image data to complete the detection of abnormal traffic.

[0053] In the embodiment of the present invention, such as figure 2 As shown, step S1 includes the following sub-steps:

[0054] S11: convert the original flow in the flow data into a grayscale image, and use the grayscale image as the G channel of the GBR image;

[0055] S12: Based on the G channel of 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 flow detection method based on a GBR image. The method comprises the following steps: S1, converting flow data into a visual GBR image; s2, storing the GBR image data in a distributed file system; and S3, based on a distributed file system, training a sub-convolutional neural network model for each data block of the GBR image data by using an Apache Spark framework to complete detection of abnormal traffic. According to the abnormal traffic detection method, the original network traffic is converted into the grayscale image, the traffic information is reserved, and then the two feature vectors are selected to form the GBR image, so that the false alarm rate of detection is reduced. The distributed file system and the sub-convolution neural network modelare used, the problems of huge calculation and slow convergence of a detection method are avoided, the capability of detecting unknown attacks is achieved, and the detection accuracy is high.

Description

technical field [0001] The invention belongs to the technical field of network traffic detection, and in particular relates to a GBR image-based abnormal traffic detection method. Background technique [0002] In recent years, with the rise of the concept of artificial intelligence, more and more machine learning has been applied to the construction of abnormal traffic detection systems, resulting in many valuable network security technologies. Most of these systems are constructed by collecting network traffic first, performing feature extraction, and then using data mining technology to perform pattern matching, so as to identify currently known attacks in an offline manner. These abnormal traffic detection systems are of high value in the promotion of network security, but there are deficiencies such as slow speed of establishing the system, complex feature extraction and high cost of resource occupancy. Based on the above situation, the present invention proposes a meth...

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): G06T5/00G06T7/90G06F16/182G06N3/04
CPCG06T7/90G06F16/182G06N3/045G06T5/90
Inventor 王彩洪孙健赵书武胡健龙
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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