Network attack detection method based on spectral clustering algorithm

A spectral clustering algorithm and network attack technology, applied to electrical components, transmission systems, etc., can solve problems such as easy to be breached, lack of attack detection and protection on the network, lack of forward-looking research on network security protection, etc., and achieve high detection rate, The effect of low false positive rate

Inactive Publication Date: 2016-09-21
YANCHENG INST OF TECH
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Domestic network protection is mainly border protection. Security devices are generally deployed at the gateway. There is no effective attack detection and protection within the network, and there is no effective monitoring method for intranet network data flow, which is easy to be breached.
Over the years, there has been a lack of fo

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be described in detail below in combination with specific embodiments.

[0022] The network attack detection method based on spectral clustering algorithm of the present invention is as follows:

[0023] (1) Input data sample set D={d 1 , d 2 ,...,d n}, where n is the size of the sample set: analyze the knowledge base, collect the data sample set, check and classify the data sample set using manual and program; research and analyze the existing detection methods at home and abroad; accurately describe the network behavior for the data sample set , and be able to distinguish between "legal" and "illegal" behaviors, while ensuring accuracy, process the feature string so that the feature string should not be too long as much as possible, which is convenient for subsequent processing.

[0024] The present invention adopts network traffic characteristic parameter technology: a method for extracting characteristic parameters of analyzing attack t...

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 attack detection method based on a spectral clustering algorithm. An NS2 network simulator is used to realize effective simulation of a denial of service (DoS) attack stream, and a DoS attack model is established. Experimental data is acquired and verified. Algebraic transformation is applied, and a spectral clustering algorithm based on a transition probability matrix is designed, and then a channel of a suspicious concealed type network attack is screened out. The network attack detection method is advantageous in that a system is designed, tested, and verified, and then the conclusion and the suggestion of the Internet attack detection method are acquired; compared with the prior art, by adopting the abnormality detection method of the spectral clustering algorithm, the false alarm rate is low, and the detection rate is high.

Description

technical field [0001] The invention relates to the field of network technology, in particular to a network attack detection method based on a spectral clustering algorithm. Background technique [0002] With the rapid development of the Internet, the advancement of industrial informatization and the integration of various networks, the network plays an important role in various enterprises and institutions, and the use of the network to process various information is also increasing. Behind the vigorous development of the Internet economy, network information security incidents occur from time to time. The dark side of cyber fraud and virus Trojan horses has also followed. At present, cyber attacks have a wide range of targets, from traditional computer Internet to various industries, such as industrial control systems, transportation, energy, aviation, mobile Internet and Internet of Things. The main purpose of cyber attacks is to steal information and obtain economic ben...

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): H04L29/06
CPCH04L63/1416H04L63/1425
Inventor 董琴季鹏宇徐森邵洪成孙久
Owner YANCHENG INST OF TECH
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