Industrial information physical system attack detection method based on two-stage auto-encoder

• Main Authors: HONG ZHEN, RAO SENBIN, WU CHAOFEI, ZHOU LEIQIANG
• Format: Patent
• Language: Chinese; English
• Published: 08.07.2022
• Subjects: CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING

The invention discloses an industrial information physical system attack detection method based on a two-stage auto-encoder. The method comprises the following steps: 1) establishing a multi-device and multi-link multi-point injection attack model; 2) introducing an auto-encoder technology; 3) constructing a generative adversarial model based on an auto-encoder; 4) designing a two-stage training method; 5) designing an attack detection algorithm; and 6) designing an attack detection method based on a two-stage auto-encoder. The adversarial network detection model based on the two-stage auto-encoder is provided by utilizing the adversarial network thought, the problems that an original generative adversarial network detection method is not easy to converge and mode collapse is easy are avoided, the condition that multiple links and multiple devices of the industrial information physical system are attacked by false data injection can be detected, and the detection accuracy is improved. And normal operation of