Rosetta: Enabling Robust TLS Encrypted Traffic Classification in Diverse Network Environments with TCP-Aware Traffic Augmentation
2023pp. 131–132
Citations Over TimeTop 10% of 2023 papers
Renjie Xie, Yixiao Wang, Jiahao Cao, Enhuan Dong, Mingwei Xu, Kun Sun, Qi Li, Licheng Shen, Menghao Zhang
Abstract
As the majority of Internet traffic is encrypted by the Transport Layer Security (TLS) protocol, recent advances leverage Deep Learning (DL) models to conduct encrypted traffic classification. We propose Rosetta to enable robust TLS encrypted traffic classification for existing DL models. It leverages TCP-aware traffic augmentation mechanisms and self-supervised learning to understand implicit TCP semantics, and hence extracts robust features of TLS flows. Extensive experiments show that Rosetta can significantly improve the classification performance of existing DL models on TLS traffic in diverse network environments.
Related Papers
- → A survey of methods for encrypted traffic classification and analysis(2015)353 cited
- → A Survey on Encrypted Traffic Classification(2014)88 cited
- → Machine learning based internet traffic recognition with statistical approach(2013)34 cited
- → New Phenomena in Large-Scale Internet Traffic(2022)14 cited
- → Are Neural Networks the Best Way for Encrypted Traffic Classification?(2021)7 cited