Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions

With the rapid growth of internet usage and the increasing number of connected devices, there is a critical need for advanced Network Traffic Classification (NTC) solutions to ensure optimal performance and robust security. Traditional NTC methods, such as port-based analysis and deep packet inspect...

Full description

Saved in:
Bibliographic Details
Main Authors: Mustafa Ghaleb, Mosab Hamdan, Abdulaziz Y. Barnawi, Muhammad Gambo, Abubakar Danasabe, Saheed Bello, Aliyu Habib
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Computer Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11023864/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849425909100052480
author Mustafa Ghaleb
Mosab Hamdan
Abdulaziz Y. Barnawi
Muhammad Gambo
Abubakar Danasabe
Saheed Bello
Aliyu Habib
author_facet Mustafa Ghaleb
Mosab Hamdan
Abdulaziz Y. Barnawi
Muhammad Gambo
Abubakar Danasabe
Saheed Bello
Aliyu Habib
author_sort Mustafa Ghaleb
collection DOAJ
description With the rapid growth of internet usage and the increasing number of connected devices, there is a critical need for advanced Network Traffic Classification (NTC) solutions to ensure optimal performance and robust security. Traditional NTC methods, such as port-based analysis and deep packet inspection, struggle to cope with modern network complexities, particularly dynamic port allocation and encrypted traffic. Recently, Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) have been employed to develop classification models to accomplish this task. Existing models for NTC often require significant computational resources due to their large number of parameters, leading to slower inference times and higher memory consumption. To overcome these limitations, we introduce a lightweight NTC model based on Depthwise Separable Convolutions and compare its performance against CNN, RNN, and state-of-the-art models. In terms of computational efficiency, our proposed lightweight CNN exhibits a markedly reduced computational footprint. It utilizes only 30,611 parameters and 0.627 MFLOPS, achieving inference times of 1.49 seconds on the CPU and 0.43 seconds on the GPU. This corresponds to roughly 4× fewer FLOPS than the RNN baseline and 16× fewer than the CNN baseline, while also offering an ultracompact design compared to state-of-the-art models. Such efficiency makes it exceptionally well-suited for real-time applications in resource-constrained environments. In addition, we have integrated eXplainable Artificial Intelligence techniques, specifically LIME and SHAP, to provide valuable insights into model predictions. LIME and SHAP help interpret the contribution of each feature in decision-making, enhancing the transparency and trust in the model’s predictions, without compromising its lightweight nature. To support reproducibility and foster collaborative development, all associated code and resources have been made publicly available.
format Article
id doaj-art-d8d3502350f944ea89517d8870acbef6
institution Kabale University
issn 2644-1268
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of the Computer Society
spelling doaj-art-d8d3502350f944ea89517d8870acbef62025-08-20T03:29:35ZengIEEEIEEE Open Journal of the Computer Society2644-12682025-01-01690892010.1109/OJCS.2025.357649511023864Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable ConvolutionsMustafa Ghaleb0https://orcid.org/0000-0003-2842-6532Mosab Hamdan1https://orcid.org/0000-0002-1008-3028Abdulaziz Y. Barnawi2https://orcid.org/0000-0003-2364-6587Muhammad Gambo3https://orcid.org/0009-0009-2918-9357Abubakar Danasabe4https://orcid.org/0009-0000-7913-0462Saheed Bello5https://orcid.org/0000-0001-5606-3383Aliyu Habib6https://orcid.org/0009-0005-6673-962XIRC for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaSchool of Computing, National College of Ireland, Dublin, IrelandDepartment of Computer Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaDepartment of Computer Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaDepartment of Computer Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaDepartment of Computer Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaDepartment of Computer Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaWith the rapid growth of internet usage and the increasing number of connected devices, there is a critical need for advanced Network Traffic Classification (NTC) solutions to ensure optimal performance and robust security. Traditional NTC methods, such as port-based analysis and deep packet inspection, struggle to cope with modern network complexities, particularly dynamic port allocation and encrypted traffic. Recently, Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) have been employed to develop classification models to accomplish this task. Existing models for NTC often require significant computational resources due to their large number of parameters, leading to slower inference times and higher memory consumption. To overcome these limitations, we introduce a lightweight NTC model based on Depthwise Separable Convolutions and compare its performance against CNN, RNN, and state-of-the-art models. In terms of computational efficiency, our proposed lightweight CNN exhibits a markedly reduced computational footprint. It utilizes only 30,611 parameters and 0.627 MFLOPS, achieving inference times of 1.49 seconds on the CPU and 0.43 seconds on the GPU. This corresponds to roughly 4× fewer FLOPS than the RNN baseline and 16× fewer than the CNN baseline, while also offering an ultracompact design compared to state-of-the-art models. Such efficiency makes it exceptionally well-suited for real-time applications in resource-constrained environments. In addition, we have integrated eXplainable Artificial Intelligence techniques, specifically LIME and SHAP, to provide valuable insights into model predictions. LIME and SHAP help interpret the contribution of each feature in decision-making, enhancing the transparency and trust in the model’s predictions, without compromising its lightweight nature. To support reproducibility and foster collaborative development, all associated code and resources have been made publicly available.https://ieeexplore.ieee.org/document/11023864/Deep learningdepthwise separable convolutioneXplainable artificial intelligenceLIMEnetwork traffic classificationSHAP
spellingShingle Mustafa Ghaleb
Mosab Hamdan
Abdulaziz Y. Barnawi
Muhammad Gambo
Abubakar Danasabe
Saheed Bello
Aliyu Habib
Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions
IEEE Open Journal of the Computer Society
Deep learning
depthwise separable convolution
eXplainable artificial intelligence
LIME
network traffic classification
SHAP
title Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions
title_full Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions
title_fullStr Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions
title_full_unstemmed Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions
title_short Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions
title_sort explainable ai for lightweight network traffic classification using depthwise separable convolutions
topic Deep learning
depthwise separable convolution
eXplainable artificial intelligence
LIME
network traffic classification
SHAP
url https://ieeexplore.ieee.org/document/11023864/
work_keys_str_mv AT mustafaghaleb explainableaiforlightweightnetworktrafficclassificationusingdepthwiseseparableconvolutions
AT mosabhamdan explainableaiforlightweightnetworktrafficclassificationusingdepthwiseseparableconvolutions
AT abdulazizybarnawi explainableaiforlightweightnetworktrafficclassificationusingdepthwiseseparableconvolutions
AT muhammadgambo explainableaiforlightweightnetworktrafficclassificationusingdepthwiseseparableconvolutions
AT abubakardanasabe explainableaiforlightweightnetworktrafficclassificationusingdepthwiseseparableconvolutions
AT saheedbello explainableaiforlightweightnetworktrafficclassificationusingdepthwiseseparableconvolutions
AT aliyuhabib explainableaiforlightweightnetworktrafficclassificationusingdepthwiseseparableconvolutions