FEAT: A Federated Approach for Privacy-Preserving Network Traffic Classification in Heterogeneous Environments
FEAT: федеративный подход к классификации сетевого трафика с сохранением конфиденциальности в гетерогенных средах
2022-09-08
SCID: 54.1/jhuju3jp
Discuss with AI
QUIC and ISCX datasetsThompson Samplingfederated analyticsfederated learningnetwork traffic classification
Figures from the paper
Abstract (AI)
Network traffic classification is the foundation for many network security and network management applications. Recently, to preserve the privacy of the data which are generated in the mobile ends, federated learning (FL)-based classification methods are being proposed. Unfortunately, the performance of FL-based methods can seriously degrade when the client data have skewness. This is particularly true for mobile network traffic classification where the environments in the mobile ends are highly heterogeneous. In this article, we first conduct a measurement study on traffic classification accuracy through FL using real-world network traffic trace and we observe serious accuracy degradation due to heterogeneous environments. We propose a novel federated analytics (FA) approach, FEAT, to improve the accuracy. Note that FL emphasizes on model training, yet our FA performs local analytic tasks that can estimate traffic data skewness and select appropriate clients for FL model training. Our analytics tasks are performed locally and in a federated manner; thus, we preserve privacy as well. Our approach has strong theoretical properties where we exploit Hoeffding inequality to infer traffic data skewness and we leverage the Thompson Sampling for client selection. We evaluate our approach through extensive experiments using real-world traffic data sets QUIC and ISCX. The extensive experiments demonstrate that FEAT can improve traffic classification accuracy in heterogeneous environments.
Key Findings
1
A measurement study using real-world traffic traces found serious federated-learning accuracy degradation under heterogeneous client environments.
2
Extensive experiments on QUIC and ISCX real-world datasets demonstrated that FEAT improves traffic-classification accuracy in heterogeneous environments.
3
FEAT is a privacy-preserving federated analytics approach that estimates local traffic-data skewness and selects suitable clients for model training.
4
FEAT performs analytics locally and federatedly, preserving the privacy of mobile-end traffic data while addressing client heterogeneity.
5
FEAT uses Hoeffding inequality to infer traffic-data skewness and Thompson Sampling for client selection, providing theoretical support for its analytics.
Research Object
privacy-preserving federated network traffic classification in heterogeneous mobile environments
Research Subject
the impact of client-data skewness and heterogeneous environments on classification accuracy, and privacy-preserving federated analytics for estimating skewness and selecting clients
Publication Details
Publication Date
2022-09-08
Journal
Publisher
ISSN
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
Deep Learning for Encrypted Traffic Classification: An Overview2019
Towards the Deployment of Machine Learning Solutions in Network Traffic Classification: A Systematic Survey2018
FedCPF: An Efficient-Communication Federated Learning Approach for Vehicular Edge Computing in 6G Communication Networks2021