Evaluating Resilience of Encrypted Traffic Classification Against Adversarial Evasion Attacks

TL;DR

This paper assesses how well various machine learning and deep learning models can withstand adversarial evasion attacks in encrypted traffic classification, revealing that deep learning generally offers better resilience.

Contribution

It provides a comparative analysis of the robustness of different ML and DL algorithms against adversarial attacks in encrypted traffic classification.

Findings

Deep learning models show higher resilience than traditional machine learning.

The effectiveness of evasion attacks varies with attack type.

Resilience depends on the specific algorithm and attack method.

Abstract

Machine learning and deep learning algorithms can be used to classify encrypted Internet traffic. Classification of encrypted traffic can become more challenging in the presence of adversarial attacks that target the learning algorithms. In this paper, we focus on investigating the effectiveness of different evasion attacks and see how resilient machine and deep learning algorithms are. Namely, we test C4.5 Decision Tree, K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). In most of our experimental results, deep learning shows better resilience against the adversarial samples in comparison to machine learning. Whereas, the impact of the attack varies depending on the type of attack.