Unlock instant, AI-driven research and patent intelligence for your innovation.

An Intrusion Detection Method for Industrial Control Systems Based on Immunity Against Samples

An industrial control system, anti-sample technology, applied in general control systems, control/regulation systems, adaptive control, etc., can solve problems such as industrial control system security threats, detection algorithm misclassification results, etc., to achieve low detection cost, high The effect of prediction accuracy

Active Publication Date: 2022-01-21
BEIJING UNIV OF TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the deepening of machine learning research, there is a problem of adversarial examples for specific algorithms.
Adversarial examples can cause the detection algorithm to produce wrong classification results, which poses a huge security threat to industrial control systems

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
  • An Intrusion Detection Method for Industrial Control Systems Based on Immunity Against Samples
  • An Intrusion Detection Method for Industrial Control Systems Based on Immunity Against Samples
  • An Intrusion Detection Method for Industrial Control Systems Based on Immunity Against Samples

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The present invention will be described in detail below in conjunction with specific embodiments shown in the accompanying drawings.

[0019] figure 1 It is a schematic structural diagram of an industrial control system intrusion detection method for immune confrontation samples, including:

[0020] The data collection module provides the collected data for the data storage module. Since the data required for training is normal samples, the data collection module provides the data storage module with the data collected during the normal production process. This process can last days or months, covering multiple industrial production cycles. The collected data should be as rich as possible for the model, and it needs to cover all special situations that may arise in the production process.

[0021] The data acquisition module provides the autoencoder detection module with data samples to be detected. Since the present invention can identify complex attacks, the acquisi...

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 intrusion detection method for an industrial control system of an immune confrontation sample. By using the historical data in the industrial control system to train the cyclic neural network, and comparing the predicted result with the real value to judge the attack, various types can be effectively identified s attack. An adversarial sample generation method for regression problems is designed to facilitate research, and an autoencoder is used for defense against this problem, so that the detection model is immune to adversarial samples. The designed method includes data storage module, data acquisition module, self-encoder detection module, recurrent neural network detection module and alarm module, which has the characteristics of high detection rate, strong real-time performance and strong innovation.

Description

technical field [0001] The invention is applied to the security field in the industrial control system, and is an intrusion detection method capable of effectively immunizing against samples. Background technique [0002] Industrial control systems (Industrial Control Systems, ICS) include distributed control systems, monitoring and data acquisition systems, etc. With the development of industrial automation technology, industrial control systems are playing an increasingly important role in industrial production. The data transmission in the industrial control system, from the earliest integrated control system to the current industrial Ethernet, has become more and more integrated with the traditional data network. More and more field devices are connected to the open Internet, which makes the security of the system The problem is more serious, and the damage caused by the attack is also more serious. [0003] In order to solve this problem, intrusion detection is applied...

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): G05B13/04
CPCG05B13/042
Inventor 赖英旭张聪刘静
Owner BEIJING UNIV OF TECH