Industrial control network misuse intrusion detection and early warning system based on edge intelligence

Abstract

The invention discloses an accurate and rapid industrial control network misuse intrusion detection and early warning system based on edge intelligence. The system is composed of a network data acquisition device, an edge intelligent computing device, a central server, a network monitoring terminal display and an intrusion alarm. The network connection data is collected by the network data acquisition device and transmitted to the edge intelligent computing device. The edge intelligent computing device comprises a data preprocessing module and an edge intelligent computing module and is used for carrying out industrial control network misuse intrusion detection and sending a detection result to the central server, the network monitoring terminal display and the intrusion alarm to carry outdisplaying and alarming. The invention provides a lightweight industrial control network misuse intrusion detection and early warning system utilizing edge intelligence, which is high in detection precision, low in false alarm rate and fast.

Description

technical field [0001] The invention relates to an accurate and fast edge intelligence-based industrial control network misuse intrusion detection and early warning system, which belongs to the technical field of industrial control security intrusion detection. Background technique [0002] Traditional industrial control systems are relatively independent and often separated from the external Internet. However, today's industrial control system is developing towards the general trend of informatization and networking. The addition of the external network breaks the original closedness. This is a double-edged sword. On the one hand, it can accelerate the development of the industrial control network. On the other hand, the industrial control network will face a series of network security problems, leading to industrial control security incidents in recent years. For example, in 2015, the control network of a Ukrainian power plant was attacked. How to effectively respond to ...

AI Technical Summary

Problems solved by technology

At present, the intrusion detection methods of industrial control systems have been based on pattern matching, time domain, frequency domain analysis, and device fingerprinting, but there are still problems of low detection accuracy and high false alarm rate.

In particular, the control site is often far away from the central server, which easily leads to delays in data processing, and there is also a high risk of data leakage during the data transmission process

Images