The Effect of Network Environment on Traffic Classification
Влияние сетевого окружения на классификацию трафика
2022-11-17
SCID: 54.1/kfwh5skq
Discuss with AI
app traffic datasetmobile app identificationmodel generalizationnetwork environmentnetwork traffic classification
Figures from the paper
Abstract (AI)
One of the challenges of network traffic classification and mobile app identification is model generalization. The accuracy and efficiency of classification models are strongly influenced by the network environment and user behavior. By changing the network environmental parameters such as mobile type or app version, the accuracy of the trained classification model may be reduced. In this paper, we investigate “how different network environments can affect the performance of a classification model?” and To this end, we have collected a dataset of 60 popular apps in Iran using different network environments.
Key Findings
1
Changing network parameters, including mobile type and application version, can reduce the accuracy of a trained classification model.
2
Network traffic classification and mobile app identification models face a generalization challenge across different network environments.
3
The authors collected a dataset covering 60 popular applications in Iran across different network environments.
4
The study investigates how variations in network environments affect classification model performance.
Research Object
network traffic classification models under different network environments
Research Subject
the effect of network-environment changes, including mobile type and app version, on classification model accuracy and efficiency/generalization
Publication Details
Publication Date
2022-11-17
Journal
Publisher
ISSN
Cited by
4
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
End-to-end encrypted traffic classification with one-dimensional convolution neural networks2017
Deep Learning for Encrypted Traffic Classification: An Overview2019
FlowPrint: Semi-Supervised Mobile-App Fingerprinting on Encrypted Network Traffic2020
A Survey of Techniques for Mobile Service Encrypted Traffic Classification Using Deep Learning2019