Growing hierarchical self-organizing maps (GHSOM)-based intrusion detection method for neural network

A self-organizing map and neural network technology, applied in the field of computer network information security, can solve the problems of increasing system overhead, not accurately reflecting the characteristics of attack behavior, and a large number of neurons

Inactive Publication Date: 2010-12-01
PEKING UNIV
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This conversion is very random and cannot accurately reflect the characteristics of the attack behavior
In addition, GHSOM grows neuron maps in each layer depending on the parameter τ 1 , parameter τ 1 Improper settings often lead to a large number of neurons, increasing the overhead of the system

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
  • Growing hierarchical self-organizing maps (GHSOM)-based intrusion detection method for neural network
  • Growing hierarchical self-organizing maps (GHSOM)-based intrusion detection method for neural network
  • Growing hierarchical self-organizing maps (GHSOM)-based intrusion detection method for neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention is described in further detail below in conjunction with accompanying drawing:

[0045] The intrusion detection system of the present invention consists of two parts: offline training of the neural network model and online detection based on the neural network model. The system collects sample data from the network as a training sample data set for offline training, and obtains an intrusion detection model for online detection. The offline training process applies the neural network training algorithm to train the neural network model based on the training data set. The trained neural network model can be applied to online network intrusion detection. Obviously, the neural network training algorithm is the core technology of the intrusion detection system based on the neural network.

[0046] Below we will focus on how to improve the GHSOM training method in combination with the training process. Then briefly introduce the process and method of ...

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 growing hierarchical self-organizing map (GHSOM)-based intrusion detection method for a neural network and belongs to the technical field of the safety of network information. A method for training a GHSOM intrusion detection model comprises the following key points of: 1) designing a new mixed vector structure which enables an improved GHSOM neural network to treat a mixed input mode vector which comprises a value type member and a character type member; and 2) designing a new control mechanism which replaces a parameter tau1 by a tension and mapping ratio (TMR), so that the GHSOM neural network supporting the mixed input mode vector automatically controls the growth of a nerve cell. Due to the application of an improved neural network in intrusion detection technology, detection rate is increased.

Description

technical field [0001] The invention relates to an intrusion detection method, in particular to an intrusion detection method based on a growing hierarchical self-organizing map (Growing Hierarchical Self-organizing Maps, GHSOM) neural network, belonging to the technical field of computer network information security. Background technique [0002] With the rapid development of computer network, especially Internet technology, network is playing an increasingly important role in our daily life, study and work, and network security issues have attracted more and more attention. It is very important to quickly and effectively discover various new intrusion behaviors to ensure the security of network systems. Intrusion detection technology is an information security technology that detects various attack attempts, attack behaviors, or attack results by monitoring the operating status of the network system. [0003] As an active defense technology, intrusion detection makes up f...

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): G06F21/00G06N3/08G06F21/55
Inventor 杨雅辉姜电波沈晴霓夏敏张英何家胜
Owner PEKING 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