A Method of Mining Vulnerabilities of Industrial Control Network Protocols Based on Counter Samples

An industrial control network and vulnerability mining technology, applied in transmission systems, electrical components, etc., can solve problems such as high redundancy and inefficiency, and achieve the effect of improving vulnerability mining capabilities and capturing exceptions.

Active Publication Date: 2021-10-22
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The research on vulnerability mining technology in the security field at home and abroad has achieved some success, but the traditional industrial control network protocol test case generation method applied to the industrial control vulnerability mining process has problems of high redundancy and low efficiency.

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 Method of Mining Vulnerabilities of Industrial Control Network Protocols Based on Counter Samples
  • A Method of Mining Vulnerabilities of Industrial Control Network Protocols Based on Counter Samples
  • A Method of Mining Vulnerabilities of Industrial Control Network Protocols Based on Counter Samples

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be described in detail below in conjunction with specific embodiments shown in the accompanying drawings.

[0021] figure 1 It is a schematic structural diagram of the generation model of the industrial control network protocol based on the anti-sample algorithm in the present invention.

[0022] The generation model consists of two parts: input-output layer and generation network. The generation network constitutes the main part of the generation model, including the protocol semantic analysis layer and the generation strategy layer. The generation strategy layer outputs the probability distribution of the current time step according to the protocol semantic analysis layer. The relationship completes the anti-sample generation strategy, and the protocol semantic analysis layer outputs the probability distribution relationship of the next time step message data value according to the message data value generated by the generation strategy laye...

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 an anti-sample-based method for mining industrial control network protocol loopholes, using Modbus TCP protocol messages as test cases to construct a loophole mining test case generation model for industrial control systems. This method first learns the semantics of the protocol data unit through the cyclic neural network and uses the Softmax layer with temperature parameters to represent the probability distribution of the data value; then compares the relationship between the random variable threshold and the maximum probability to decide whether to replace it with a data value with a very small probability The current data value is used to increase the possibility of abnormal industrial control, and finally, according to the protocol specification, random values ​​are used to supplement the protocol MBAP message header to form a complete test case. The method can solve the high redundancy and inefficiency problems of the industrial control network protocol, and improve the vulnerability mining ability of use cases.

Description

technical field [0001] The invention relates to the field of industrial control network security, in particular to a method for semantic learning and vulnerability mining of industrial control network protocols based on counter samples. Background technique [0002] With the introduction of Internet technologies such as Industry 4.0, industrial control systems continue to closely integrate automation and intelligence, and network security risks also follow. Industrial control systems are widely used in energy, water conservancy, transportation, manufacturing and other fields, and the number of exploiting vulnerabilities to attack industrial control equipment continues unabated. [0003] In recent years, there have been multiple serious security vulnerabilities in the MicroLogix 1400 series PLC of Rockwell Automation, causing denial of service attacks, tampering with device configuration and other attacks; the website of the Ministry of Energy and Coal Industry of Ukraine was...

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): H04L29/06
CPCH04L63/1425H04L63/1433H04L69/03
Inventor 赖英旭高慧娟刘静冯文倩王志东
Owner BEIJING UNIV 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

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