Multi-point FDI attack detection method for industrial information physical system of generative adversarial network

Abstract

The invention discloses a multi-point FDI attack detection method for an industrial information physical system of a generative adversarial network. The method comprises the following steps of 1) establishing different types of FDI attack models, 2) establishing a GAN model, 3) establishing an LR-GAN model using an LSTM-RNN as a generator unit and a discriminator unit, 4) designing a multi-point FDI attack detection algorithm based on LR-GAN, and 5) designing a multi-point FDI attack detection framework based on the LR-GAN. According to the method, the novel generative adversarial network is used, normal operation of the ICPS system can be guaranteed under the condition that FDI attacks exist in multiple links and multiple devices, and the safety performance of the system is improved while the attacks are detected. In addition, a new multi-point FDI attack detection algorithm is designed, and a FDI attack detection framework based on LR-GAN is provided at the same time.

Description

technical field [0001] The present invention relates to the field of security control and operation of industrial cyber-physical system (Industrial Cyber-Physical System, ICPS), in particular to a multi-point false data injection attack (False Data Injection, FDI) detection method based on generative confrontation network, which is applied to ICPS To solve the problem of FDI attack detection for multi-link or multi-device. Background technique [0002] As ICPS begins to be applied in various industrial systems, people no longer have to go to the industrial site for manual physical operations, but use the distributed remote control feature of ICPS to pass Programmable Logic Controller (Programmable Logic Controller, PLC) and sensors, etc. Smart devices control and monitor the system. For the control network combined by these PLCs and sensors, the staff can use the supervisory control and data acquisition system (Supervisory Control And Data Acquisition, SCADA) combined with ...

AI Technical Summary

Problems solved by technology

[0006] (2) Based on process data analysis: Process data information is an important factor to be considered in the ICPS attack detection system. FDI attacks mislead the controller to make wrong decisions by tampering with process information, and eventually cause fatal damage to the system.

[0007] Although the above two methods have good detection results for conventional FDI attacks, the existing detection methods cannot be effective for multi-point FDI attacks launched by high-level attackers, that is, injecting false data on multiple links or multiple devices.

Images