Method for training encrypted traffic data classification model and method for classifying encrypted traffic data

Abstract

The application provides a training method of an encrypted traffic data classification model and a classification method of encrypted traffic data. The training method of the encrypted traffic data classification model generates a plurality of augmented data samples by performing multiple disturbance processes on unannotated first encrypted traffic data samples through a data augmenter, and the difference between each augmented data sample and the first encrypted traffic data sample is less than a preset threshold; determines pseudo-label data samples according to the plurality of augmented data samples through a pseudo-label generator; inputs annotated second encrypted traffic data samples and the pseudo-label data samples into an initial encrypted traffic data classification model as training data, and obtains a predicted classification result output by the initial encrypted traffic data classification model; and updates model parameters of the initial encrypted traffic data classification model according to actual classification results corresponding to the training data and the predicted classification result, to obtain a trained encrypted traffic data classification model. The model generalization capability can be improved.

Images