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

Machine learning-based attack detection method for non-analyzable network data feature selection

An attack detection and machine learning technology, applied in machine learning, instruments, computer components, etc., can solve the problems of poor model robustness, variable attack forms, lack of research on encrypted and unanalyzed network data attack detection, etc. To achieve the effect of reducing the occurrence of safety accidents

Active Publication Date: 2020-06-19
ZHEJIANG UNIV
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing industrial control network attack detection methods are mainly aimed at general analyzable network data, and the attack detection research on encrypted and unanalyzed network data is still lacking. The robustness is poor, and the integrated learning method with high generalization ability can be applied to network attack detection

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
  • Machine learning-based attack detection method for non-analyzable network data feature selection
  • Machine learning-based attack detection method for non-analyzable network data feature selection
  • Machine learning-based attack detection method for non-analyzable network data feature selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the above objects, features and advantages of the present invention more comprehensible, specific implementations of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0030] In the following description, a lot of specific details are set forth in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described here, and those skilled in the art can do it without departing from the meaning of the present invention. By analogy, the present invention is therefore not limited to the specific examples disclosed below.

[0031] Using a typical industrial control network security test platform, the on-site control layer adopts the domestic SUPCON ECS700 controller, and the on-site device layer uses cascaded water tanks as the control object. The industrial control network attack detection process is given, including the following...

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 machine learning-based attack detection method for non-analyzable network data feature selection. The method is composed of three parts of data acquisition preprocessing, feature extraction and construction and attack detection model establishment and detection based on machine learning. The data preprocessing part is used for carrying out numeralization on network data;the feature extraction and construction part completes construction of data features based on data packet period and length information on the basis of deep analysis of industrial control network attacks. The modeling part is used for establishing an industrial control network attack detection model based on a machine learning classification method. According to the invention, attack forms such asre-amplification flow attack and man-in-the-middle attack in the industrial control system network can be accurately detected in real time, and safety accidents and economic losses caused by the safety accidents are reduced.

Description

technical field [0001] The invention relates to an attack detection method of an industrial control network, specifically, a method for detecting specific attacks of an industrial control network by using machine learning and based on characteristic engineering of data packets of the industrial control network, and belongs to the technical field of industrial control network security. Background technique [0002] The Industrial Internet is an industry and application ecology formed by the all-round and deep integration of the Internet and the new generation of information technology with the global industrial system. It is the key comprehensive information infrastructure for the development of industrial intelligence. Large-scale industrial control networks bring intelligent and convenient remote control of equipment, but also make them more vulnerable to cyber attacks. High-tech cyber attack methods are constantly emerging, and viruses are becoming more and more complex. O...

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): H04L29/06G06K9/62G06N20/00
CPCH04L63/1416G06N20/00G06F18/2411G06F18/214
Inventor 黄文君米俊芃陈梦迟王宇平
Owner ZHEJIANG 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