Network traffic classification method and system based on multi-scale feature attention

Abstract

The invention discloses a network traffic classification method and system based on multi-scale feature attention. The method comprises a training stage and a classification stage. The training stage comprises the following steps: uniformly processing traffic samples of an application protocol; learning and training the training data, and constructing an application protocol classification model. The classification stage comprises the steps of collecting network traffic and performing unified processing; and according to the application protocol detection model obtained in the training stage, judging the application protocol type of the to-be-detected traffic sample, and outputting a judgment result. According to the method, potential feature information of different scales in the network traffic can be fully mined, so that feature representation with better expression ability is formed, and the method has high accuracy and strong robustness in a network application protocol traffic classification process.

Description

technical field [0001] The invention relates to a method and system for automatically classifying mixed network traffic using deep learning technology according to the payload of message grouping, in particular to a method and system for classifying network traffic based on multi-scale feature attention, belonging to the technical field of network traffic classification . Background technique [0002] Network traffic classification is the process of associating network traffic with specific application protocols or applications that it generates. It has important applications in the fields of network management and network security, such as network measurement, tunnel detection, quality of service (QoS), and intrusion detection and defense etc. Specifically, in network management, in order to obtain better service quality and network provisioning, network operators first need to divide traffic into different application protocols. Also, in the field of network security, ne...

AI Technical Summary

Problems solved by technology

It is worth noting that although GPUs have a lot of computing power, the sequential nature of RNNs makes GPUs have to wait for data to become available.

Therefore, the RNN-based network traffic classification method has great limitations in computational efficiency and computational complexity.

Images