LDoS attack detection method based on integrated wavelet transform in SDN environment

A wavelet transform and attack detection technology, applied in the field of signal processing, can solve the problems of controller failure, low speed, switch and controller damage, etc., to improve the speed and accuracy, and reduce the burden.

Active Publication Date: 2021-04-09
GUIZHOU UNIV
View PDF16 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] LDoS attack is to send the attack flow at a low rate and periodically, so that the victim end is continuously attacked without being noticed, which affects the availability of SDN
In view of the different architectures of SDN and traditional networks, LDoS attacks in SDN have different characteristics from traditional networks: in SDN, LDoS attacks can also cause damage to switches and controllers, and consume a large amount of switch resources, making The channel resources between the controller and the switch are exhausted, causing the controller to fail

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
  • LDoS attack detection method based on integrated wavelet transform in SDN environment

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0026] according to figure 1 As shown, the present invention provides an LDoS attack detection method based on integrated wavelet transform under a kind of SDN environment, comprises the following steps:

[0027] Step 1: use a variety of different wavelet transform basis functions to calculate the entropy value sets of different wavelet energy spectra;

[0028] Step 2: Randomly select the wavelet basis function from the wavelet basis function library, which is assumed to be the Daubechies basis function here;

[0029] Step 3: Based on the Daubechies basis function, recursively perform wavelet decomposition on the low-pass approximation coefficients obtained by each layer in order to extract the characteristics of the flow entry, and obtain each coefficient matrix correspondingly, and judge whether the number of the selected wavelet basis functions reaches the specified integration When the number of wavelet basis functions reaches the specified value, it is completed;

[003...

specific Embodiment 2

[0042] The purpose of the present invention is to utilize the multidimensionality and diversity advantage of the energy spectrum entropy value that multiple different wavelet basis functions extract, be applied to the detection of the LDoS attack in the SDN environment, improve the detection accuracy of the LDoS attack, avoid the detection of the LDoS attack Inaccurate positioning and positioning cause the consumption of a large amount of resources in the SDN network.

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 relates to an LDoS attack detection method based on integrated wavelet transform in an SDN environment. The invention relates to the technical field of signal processing. The method comprises the steps that entropy sets of different wavelet energy spectrums are obtained through calculation by means of multiple different wavelet transform basis functions; randomly selecting a wavelet basis function from a wavelet basis function library; judging whether the number of the selected wavelet basis functions reaches the number of specified integrated wavelet basis functions or not, and decomposing by utilizing three different wavelet basis functions; extracting the detail coefficients of each coefficient matrix are extracted, calculating an integrated wavelet energy value to acquire an entropy set of an integrated wavelet energy spectrum, allocating corresponding labels, and selecting a part of data set to train a support vector machine model and a full-connection neural network model; and detecting LDoS attacks in the SDN network by using the trained support vector machine model and the full-connection neural network model, sending a warning message if the LDoS is detected, and discarding data packets corresponding to the flow table entries, thereby reducing the load of the SDN network.

Description

technical field [0001] The invention relates to the technical field of signal processing, and relates to an LDoS attack detection method based on integrated wavelet transform in an SDN environment. Background technique [0002] Software-Defined Networking (SDN) is one of the next-generation network structures widely recognized as being able to replace the current network. Different from the traditional network structure, SDN realizes the decoupling of the control plane and the data forwarding plane, and has the advantages of network programmability, global visibility, and unified management. Although SDN is widely used, SDN is facing serious security problems, which restrict the development and application of SDN. Low Denial of Service (LDoS) attack is one of the more serious network security problems in SDN. [0003] Discrete Wavelet Transform (DWT) realizes signal processing by discretizing the scale and translation of the basic wavelet, which belongs to an analysis 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
Patent Type & Authority Applications(China)
IPC IPC(8): H04L29/06
CPCH04L63/1416H04L63/1458Y02D30/50
Inventor 崔允贺王聪申国伟高鸿峰
Owner GUIZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap