Traditional network traffic detection methods based on machine learning have been widely used, but the accuracy of identifying and detecting abnormal traffic is not high. Compared with machine learning methods, deep learning has made significant progress in fields such as text processing, video generation, and other fields, bringing new ideas to abnormal traffic detection. This paper adopts an abnormal traffic classification method based on multi-pooling cascaded convolutional neural network (MPCNN). The accuracy of extensive experiments is 0.9914, the precision is 0.9984, and the F1 score is 0.9962. These experiments achieved the company's goal of accuracy greater than 0.98. It is used for real-time monitoring of daily network traffic to recognize abnormal traffic virtually, alert topic timely, and prevent potential network threats.
Abnormal Network Traffic Detection Based on Multi-Pooling Cascaded MPCNN
2025-01-17
681058 byte
Conference paper
Electronic Resource
English
European Patent Office | 2020
|Railway traffic pooling scheme
Engineering Index Backfile | 1932
Multi-mode integrated traffic abnormal event detection method
European Patent Office | 2024
|Detection of email attack in encrypted network traffic based on abnormal behavior analysis
British Library Conference Proceedings | 2022
|