A Feasible and Explainable Network Traffic Classifier Utilizing DistilBERT

Chang-Yui Shin

doi:10.1109/ACCESS.2023.3293105

2023-01-01

DOI：10.1109/ACCESS.2023.3293105

原文链接

原文求助

摘要

En 中文

While user-oriented service industries are rapidly growing, various network devices provide these services through different access paths. Accordingly, the network flow is also increasing explosively. As demand for management related to limited network resources increases, the network traffic classification grows to prominence. Usually, a quick classification task was possible with hundreds of data composed of dozens of features. Afterward, deep learning models have proliferated owing to an outstanding performance that overwhelms existing performance based on hundreds of thousands of features and data. However, the deep learning models showing one of the best performances cannot be free from two facts. One is a lot of time and resource consumption. The other is an uncertain explanation of the process. We solved these problems. Firstly, we used two methods to overcome resource constraints. We modified the DistilBERT applied with knowledge distillation for using a compressed model and securing a remarkable performance. We used a lightweight packet with a header and partial payload for feature reduction. Consequently, our XENTC can process four multi-attribute packets simultaneously and effectively by removing the superfluity of features. And it achieved 97.0 similar to 98.1% F1 scores. The required time to classify a packet using a trained model is 0.0093 seconds. Therefore, it can be one of the feasible solutions. Secondly, to approach human-understandable XAI, we analyzed the relationships between the features by associating them with the packet structure. At the specific point of the model's finished training, it was revealed what the important features of the packet were by counting the Top-5 number of times among the attention values. In addition, we visualized the classification performance of the model using t-SNE to enable intuitive understanding.

Keyword:

Encrypted network traffic classification

deep learning

NLP

BERT

knowledge distillation

DistilBERT

XAI

期刊

IEEE Access

IF:

3.6

论文数:

9.8W

被引数:

29.4W

机构

Korea University

学者数:

3.6W

论文数: 3.8W

被引数: 4.4W

引用论文

Quantification of kynurenic acid in cerebrospinal fluid: effects of systemic and central l-kynurenine administration

Journal of Chromatography B: Biomedical Sciences and Applications

IF0

1990-01-01

PREAI

Melvyn P. Heyes; Bonnie J. Quearry

Facile Synthesis and Characterization of CuO–CeO₂ Nanostructures for Photocatalytic Applications

Crystal Research and Technology

IF0

2022-02-20

PREAI

Muhammad Arfan; Intisar Hussain; Zahoor Ahmad; Andleeb Afzal; Tauseef Shahid; Abdul Ghafar Wattoo; Muhammad Rafi; Aurang Zeb; Muhammad Imran Shahzad; Song Zhenlun

Repeated and Time-Correlated Morphological Convergence in Cave-Dwelling Harvestmen (Opiliones, Laniatores) from Montane Western North America

PLoS ONE

IF0

2010-05-07