Industrial control environment intelligent safety detection system and method based on machine learning

Abstract

The invention discloses an industrial control environment intelligent safety detection system and method based on machine learning. A security probe device is deployed based on an industrial control internal network, and can be used for realizing information security condition and situation awareness of an industrial control environment. A machine learning algorithm is built in the safety probe device, and the detection algorithm factor addition of the safety probe comprises the contents of realizing an application white list, configuring compliance check and patch scanning, a normal industrial control protocol and abnormal industrial control protocol list and the like. The probe equipment provided by the invention can be widely applied to severe environments with high heat, dust and the like in industrial production, and has more deployment advantages compared with an industrial control probe in a conventional standard machine room environment.

Description

technical field [0001] The invention relates to the technical field of industrial control security, in particular to an intelligent security detection system and method for an industrial control environment based on machine learning. Background technique [0002] With the development of wireless and mobile networks, network information security has brought huge hidden dangers to industrial control network facilities. Coupled with the improvement of the network access capabilities of various smart instruments and operating terminals, the inherent vulnerabilities and attack surfaces of industrial control systems are increasing. . [0003] The document "Research on Machine Learning-Based Perceptible Sequential Industrial Control Intrusion Detection Technology" was published on China National Vulnerability Database (CNVD) and China National Vulnerability Database of Information Security (CNNVD) The vulnerabilities were classified and statistically analyzed. The results show t...

AI Technical Summary

Problems solved by technology

[0008] Models and lists established offline are difficult to adapt to new situations in the changing industrial process network environment. For example, it is difficult to detect new intrusion methods based on the intrusion detection model established based on old rules, and it is difficult to detect the intrusion of new abnormal protocols based on the old abnormal protocol list.

Images