Analysis of Private Industrial Control Protocol Format Based on LSTM-FCN Model
Rui Zhao, Zhaohui Liu
Abstract
Protocol security is an important element in the field of industrial control system security. For industrial control systems filled with a large number of private protocols, accurate information on the format of private industrial control protocols is the basis of its security analysis. How to effectively analyze the format of private industrial control protocols is the key point to be solved in the security of the current industrial control system. In this paper, a private industrial control protocol formats analysis method based on Long short-term memory Fully convolutional neural network (LSTM-FCN) is proposed. The Long short-term memory Fully convolutional neural network (LSTM-FCN) model is used to learn the field types of public industrial control protocols. The trained model is then applied to the private industrial control protocols field type identification. Finally, the type recognition fields are fused based on the format characteristics of the public protocol fields. The results of the format analysis of the private industrial control protocol were obtained. The experimental results show that the method can accurately analyze the format of private industrial control protocols.