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

A network attack defense method and system based on machine learning under the SDN architecture

A technology of SDN architecture and network attack, applied in the field of network security

Active Publication Date: 2021-02-02
BEIJING UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to solve the real-time problem of network traffic detection, the present invention does not use the features that can only be obtained when the network traffic ends when selecting features, and at the same time, in order to improve the accuracy of network attack recognition, the present invention designs a message information library , used to store historical message information, and use the connection between historical messages and current messages as new features to identify network attacks, which not only solves the real-time problem of network attack identification, but also uses new statistical features The problem of insufficient features is alleviated by adding

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
  • A network attack defense method and system based on machine learning under the SDN architecture
  • A network attack defense method and system based on machine learning under the SDN architecture
  • A network attack defense method and system based on machine learning under the SDN architecture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Aiming at the existing network security problems, the present invention designs a set of network attack defense methods and systems based on machine learning, and uses the network attack recognition model trained by machine learning to effectively identify the attack behaviors existing in the network and make network attacks take appropriate defensive measures.

[0031] First, a deep fully connected network is constructed as a network attack detection model, and the number of received statistical features (ie, input dimension values) and the number of output parameters (ie, output dimension values) are set in this model. The present invention sets the input dimension to 17, representing 17 features of the current message, including two types of basic attribute features of the message and statistical features of the current message and historical messages, such as protocol type, target host network service type, connection The normal or error state, etc., are shown in Ta...

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 present invention discloses a network attack defense method and system based on machine learning, using machine learning to train a network attack identification model, and then deploying the model on an SDN controller, and using the machine learning model to process messages uploaded by switches Detection, according to the detection results to make corresponding defense measures, and finally achieved the effect of successful defense against 99.97% of network attacks.

Description

technical field [0001] The invention belongs to the technical field of network security, and in particular relates to a machine learning-based network attack defense method and system under the SDN framework. Background technique [0002] With the development of network technology, the Internet makes people's life more and more convenient, but the subsequent network security issues are exposed to people. In traditional networks, firewalls are used as the first line of defense for security. However, due to the rapid improvement of network attackers' technologies and methods, network attacks are more difficult to defend against. The defense of the network must also adopt a fine-grained, adaptable s method. [0003] SDN is a new type of network architecture. The design concept is to separate the control plane of the network from the data forwarding plane and realize programmable control. The SDN architecture is usually divided into three layers, the top layer is the applicati...

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 Patents(China)
IPC IPC(8): H04L29/06G06N20/00
Inventor 霍如薛宁刘江黄韬鄂新华谢人超晁代崇刘韵洁
Owner BEIJING UNIV OF TECH
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