Training method and device of flow recognition model and electronic equipment

Abstract

The embodiment of the invention provides a traffic recognition model training method and device and electronic equipment, and relates to the technical field of industrial control. The training methodof the traffic recognition model comprises the following steps: acquiring a sample traffic set; wherein the sample flow set comprises sample feature information of a plurality of detected protocol flows; dynamically determining a first number of clustering centers according to sample feature information in the sample flow set so as to divide the sample flow set into a plurality of sample clustersaccording to the obtained first number; and training a preset machine learning model by using the obtained sample cluster to obtain the flow recognition model. In this way, samples in the sample flowset can be automatically and accurately classified even if priori knowledge does not exist. Therefore, the recognition precision of the obtained flow recognition model is improved.

Description

technical field [0001] The invention relates to the technical field of industrial control, in particular to a training method, device and electronic equipment for a flow recognition model. Background technique [0002] With the advancement of networking and informatization in the field of industrial control, industrial control network systems are becoming larger and more open. However, the industrial control network system has high requirements on the quality of data transmission, and is extremely sensitive to events such as viruses that affect system security. Therefore, industrial control network security has become a severe challenge in the field of industrial control. [0003] Identifying whether the industrial control protocol traffic is normal is the first step to ensure the security of the industrial control network. Traffic identification based on machine learning is a promising traffic identification method. However, at present, in order to ensure the accuracy of...

AI Technical Summary

Problems solved by technology

However, in order to ensure the accuracy of machine learning, a large number of samples are required to train the traffic recognition model

It is necessary to manually specify the number of sample categories before training. For samples that represent new and small amounts of abnormal traffic, due to the lack of prior knowledge, the classification of samples is not accurate enough, resulting in the traffic recognition model obtained by training. The accuracy of the traffic recognition model is not ideal in practical applications.

Images