Robust Machine Learning for Encrypted Traffic Classification

TL;DR

This paper develops robust machine learning methods to classify encrypted network traffic, achieving high accuracy and resilience against adversarial attacks and network variability, using a large dataset and comprehensive experiments.

Contribution

It introduces a robust classification approach for encrypted traffic, demonstrating high accuracy and robustness under various network conditions and limited training data.

Findings

Achieves over 85% classification accuracy.

Demonstrates robustness against feature changes and network conditions.

Shows effectiveness with small training datasets.

Abstract

Desktops and laptops can be maliciously exploited to violate privacy. In this paper, we consider the daily battle between the passive attacker who is targeting a specific user against a user that may be adversarial opponent. In this scenario, while the attacker tries to choose the best vector attack by surreptitiously monitoring the victims encrypted network traffic in order to identify users parameters such as the Operating System (OS), browser and apps. The user may use tools such as a Virtual Private Network (VPN) or even change protocols parameters to protect his/her privacy. We provide a large dataset of more than 20,000 examples for this task. We run a comprehensive set of experiments, that achieves high (above 85) classification accuracy, robustness and resilience to changes of features as a function of different network conditions at test time. We also show the effect of a small training set on the accuracy.