Hidden attack detection method based on multi-scale sample entropy and Bayesian network

Abstract

A hidden attack detection method based on a multi-scale sample entropy and a Bayesian network adopts the technical scheme that 1, information of a plurality of physical sensors of a networked motion control system is analyzed, so that the effect of the provided method is better than that of a method based on a single sensor; 2, from the perspective of data driving, sensor information existing in a networked motion control system is fully utilized, and an accurate control system model is not depended on; and 3, through simple coarse graining operation, more information is obtained with low calculation cost, and certain detection performance is improved while the real-time performance of the networked motion control system is met. And 4, the Bayesian network is combined with certain priori knowledge, has better generalization ability, is extremely high in calculation efficiency, and is a detection method very suitable for a networked motion control system.

Description

technical field [0001] The invention belongs to the technical field of industrial control system safety, and in particular relates to an intrusion detection method suitable for concealed attacks on a networked motion control system to ensure the normal operation of the networked motion control system. Background technique [0002] With the increasing improvement of networked motion control system technology, various advanced technologies such as embedded technology, multi-standard industrial control network interconnection, and wireless technology have been organically integrated, expanding the development space in the field of industrial control. The advanced communication network technology makes the traditional motion control system begin to develop in the direction of networking, and the closedness of the system is broken, which leads to the networked motion control system facing information security threats such as viruses, Trojan horses, and hackers. [0003] There are...

AI Technical Summary

Problems solved by technology

[0004] In order to target the hidden attacks in the existing networked motion control systems, the detection methods usually start from the control theory. This type of method requires an accurate control theory model, but it is difficult to obtain in practical applications, and the complexity of the industrial control system protocol Insufficiency that makes it difficult to implement computer security technology, the present invention considers the situation that the networked motion control system under multiple sensors is under covert attack, and detects whether there is a sinusoidal attack in the networked motion control system according to the multi-sensor data feature fusion technology

Images