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

Network intrusion detection model based on random forest algorithm

A technology of network intrusion detection and random forest algorithm, applied to electrical components, transmission systems, etc., can solve the problems of unfavorable model establishment, unbalanced data set distribution, uncleanness, etc., and achieve excellent results, efficient establishment, and less time Effect

Active Publication Date: 2018-11-06
SUN YAT SEN UNIV
View PDF3 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In general, the traffic data of attack types is very small, the distribution of data sets is unbalanced, and there are many unclean data in network traffic, that is, noise data, which is not conducive to the establishment of a good model

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 intrusion detection model based on random forest algorithm
  • Network intrusion detection model based on random forest algorithm
  • Network intrusion detection model based on random forest algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The drawings are for illustrative purposes only, and should not be construed as limitations on this patent; in order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0035] For those skilled in the art, it is understandable that some well-known structures and descriptions thereof may be omitted in the drawings. The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0036] A network intrusion detection model based on random forest algorithm, comprising the following steps:

[0037] Step 1: Read the data set, delete redundant redundant data in the data set, then perform feature selection, use each feature to divide the data set, and calculate the information entropy of the data subset after division, so as to obtain information gain. The information gain is sorted from large...

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 intrusion detection model based on a random forest algorithm, which adopts the steps of: inputting training data, and after reading the training data, firstly carrying out preprocessing on the data; and then training the data by applying the random forest algorithm, and establishing an intrusion detection model. Data preprocessing is formed by five steps of: a first step of deleting a redundancy part in the data, i.e., deleting repeated data in the data; a second step of carrying out feature selection, i.e., by carrying out sorting from big to small on information gains, selecting first 70% of features; a third step of artificially synthesizing a new data set, i.e., due to unbalance of data distribution, artificially synthesizing the new data set by usinga SMOTE (Synthetic Minority Oversampling Technique) algorithm; a fourth step of carrying out data cleaning, i.e., carrying out a cleaning operation on the data by using an ENN (Edited Nearest Neighbor) algorithm; and a fifth step of carrying out regularization processing, i.e., carrying out regularization processing on the data, so that a range of each feature is centralized in a specific range.

Description

technical field [0001] The invention relates to the field of intrusion detection network security, in particular to a network intrusion detection model based on a random forest algorithm. Background technique [0002] Intrusion detection refers to collecting information from key points in a computer network, and analyzing the information to see if there is a violation of security policies in the network. Intrusion detection can be said to be a reasonable supplement and extension of firewall; if firewall is the first security gate, intrusion detection can be said to be the second security gate. On the premise of not affecting network performance, intrusion detection can protect various internal and external attacks in real time and dynamically, and at the same time effectively make up for the protection limit that firewalls can achieve. [0003] The traditional intrusion detection technology is a technology that applies the rule set method to detect violations of security po...

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
CPCH04L63/1416
Inventor 周杰英杨诗珺邱荣发刘映淋
Owner SUN YAT SEN 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