Man-in-the-middle attack detection method for gas SCADA system based on single classification support vector machine

Abstract

The invention discloses a man-in-the-middle attack detection method for a gas pipe network SCADA system based on a single classification support vector machine. The man-in-the-middle attack detection method comprises the following steps: 1) performing feature extraction on valve switch signal data returned by a gas pipe network SCADA system sensor; 2) firstly, training a single classification support vector machine model by using data sets operated under all normal working conditions of the gas SCADA system; secondly, verifying the accuracy of the model by using a verification set, verifying the generalization ability of the single classification support vector machine model by using a test set, and finding an optimal single classification support vector machine model by continuously adjusting a kernel function and penalty parameters; and 3) real-time attack detection: returning a valve switch signal of the gas SCADA system in real time according to the sampling time, carrying out coding calculation on the signal, putting the data characteristics into the trained support vector machine model, and judging whether the valve at the sampling time point is attacked or not. According to the method, the man-in-the-middle attack of the gas SCADA system is effectively detected.

Description

technical field [0001] The invention relates to the field of gas SCADA system attack detection and specifically designs a gas SCADA system man-in-the-middle attack detection method based on a single classification support vector machine. Background technique [0002] As a clean, low-emission and efficient energy source, natural gas has a good substitute for traditional energy sources in power generation, transportation, and chemical industry. With the continuous expansion of the urban natural gas pipeline network, the manual management mode and management methods can no longer meet the requirements of "reasonable planning, scientific management, and safe gas use". The response capacity and processing efficiency for emergencies are difficult to meet the needs of the rapid development of urban construction. Therefore, natural gas companies need a more convenient and timely way to realize the automation and scientificity of pipeline network operation, pipeline maintenance, pip...

AI Technical Summary

Problems solved by technology

[0004] The urban gas high-pressure pipeline network has the greatest impact on the entire city. Because the man-in-the-middle attack has invaded the gas SCADA system, it is difficult to detect at the network layer. Once a man-in-the-middle attack occurs, it may cause casualties and major property losses, and affect people's health normal production and life

Images