L2R-MLP: a multilabel classification scheme for the detection of DNS tunneling

Domain name system (DNS) tunneling attacks can bypass firewalls, which typically “trust” DNS transmissions by concealing malicious traffic in the packets trusted to convey legitimate ones, thereby making detection using conventional security techniques challenging. To address this issue, we propose...

Full description

Saved in:
Bibliographic Details
Main Authors: Emmanuel Oluwatobi Asani, Mojiire Oluwaseun Ayoola, Emmanuel Tunbosun Aderemi, Victoria Oluwaseyi Adedayo-Ajayi, Joyce A. Ayoola, Oluwatobi Noah Akande, Jide Kehinde Adeniyi, Oluwambo Tolulope Olowe
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2025-09-01
Series:Data Science and Management
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666764924000560
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849222526760124416
author Emmanuel Oluwatobi Asani
Mojiire Oluwaseun Ayoola
Emmanuel Tunbosun Aderemi
Victoria Oluwaseyi Adedayo-Ajayi
Joyce A. Ayoola
Oluwatobi Noah Akande
Jide Kehinde Adeniyi
Oluwambo Tolulope Olowe
author_facet Emmanuel Oluwatobi Asani
Mojiire Oluwaseun Ayoola
Emmanuel Tunbosun Aderemi
Victoria Oluwaseyi Adedayo-Ajayi
Joyce A. Ayoola
Oluwatobi Noah Akande
Jide Kehinde Adeniyi
Oluwambo Tolulope Olowe
author_sort Emmanuel Oluwatobi Asani
collection DOAJ
description Domain name system (DNS) tunneling attacks can bypass firewalls, which typically “trust” DNS transmissions by concealing malicious traffic in the packets trusted to convey legitimate ones, thereby making detection using conventional security techniques challenging. To address this issue, we propose a Lebesgue-2 regularized multilayer perceptron (L2R-MLP) algorithm for detecting DNS tunneling attacks. The DNS dataset was carefully curated from a publicly available repository, and relevant features, such as packet size and count, were selected using the recusive feature elimination technique. L2 regularization in the MLP classifier's hidden layers enhances pattern recognition during training, effectively countering the risk of overfitting. When evaluated against a benchmark MLP model, L2R-MLP demonstrated superior performance with 99.46% accuracy, 97.00% precision, 97.00% F1-score, 99.95% recall, and an AUC of 89.00%. In comparison, the benchmark MLP achieved 92.53% accuracy, 96.00% precision, 97.00% F1-score, 99.95% recall, and an AUC of 87.00%. This highlights the effectiveness of L2 regularization in improving predictive capabilities and model generalization for unseen instances.
format Article
id doaj-art-0de976b0bf574529867f003cbc9c70bd
institution Kabale University
issn 2666-7649
language English
publishDate 2025-09-01
publisher KeAi Communications Co. Ltd.
record_format Article
series Data Science and Management
spelling doaj-art-0de976b0bf574529867f003cbc9c70bd2025-08-26T04:14:35ZengKeAi Communications Co. Ltd.Data Science and Management2666-76492025-09-018332333110.1016/j.dsm.2024.10.005L2R-MLP: a multilabel classification scheme for the detection of DNS tunnelingEmmanuel Oluwatobi Asani0Mojiire Oluwaseun Ayoola1Emmanuel Tunbosun Aderemi2Victoria Oluwaseyi Adedayo-Ajayi3Joyce A. Ayoola4Oluwatobi Noah Akande5Jide Kehinde Adeniyi6Oluwambo Tolulope Olowe7Department of Computer Science, Landmark University, Omu-Aran, 251103, Nigeria; Landmark University SDG 11, Landmark University, Omu-Aran, 251103, Nigeria; Department of Computer Science, WestMidland University, Lagos, 100001, NigeriaDepartment of Computer Science, Landmark University, Omu-Aran, 251103, NigeriaDepartment of Computer Science, Landmark University, Omu-Aran, 251103, Nigeria; Landmark University SDG 8, Landmark University, Omu-Aran, 251103, Nigeria; Corresponding author. Department of Computer Science, Landmark University, Omu-Aran, Nigeria.Department of Computer Science, Landmark University, Omu-Aran, 251103, Nigeria; Landmark University SDG 8, Landmark University, Omu-Aran, 251103, Nigeria; Department of Cyber Security Science, Ladoke Akintola University of Technology, Ogbomosho, 210214, NigeriaElectrical and Computer Engineering, Santa Clara University, Santa Clara, CA 95035, USAComputer Science Department, Baze University, Abuja, 900211, NigeriaDepartment of Computer Science, Landmark University, Omu-Aran, 251103, Nigeria; Landmark University SDG 9, Landmark University, Omu-Aran, 251103, NigeriaDepartment of Computer Science, Landmark University, Omu-Aran, 251103, Nigeria; Landmark University SDG 9, Landmark University, Omu-Aran, 251103, NigeriaDomain name system (DNS) tunneling attacks can bypass firewalls, which typically “trust” DNS transmissions by concealing malicious traffic in the packets trusted to convey legitimate ones, thereby making detection using conventional security techniques challenging. To address this issue, we propose a Lebesgue-2 regularized multilayer perceptron (L2R-MLP) algorithm for detecting DNS tunneling attacks. The DNS dataset was carefully curated from a publicly available repository, and relevant features, such as packet size and count, were selected using the recusive feature elimination technique. L2 regularization in the MLP classifier's hidden layers enhances pattern recognition during training, effectively countering the risk of overfitting. When evaluated against a benchmark MLP model, L2R-MLP demonstrated superior performance with 99.46% accuracy, 97.00% precision, 97.00% F1-score, 99.95% recall, and an AUC of 89.00%. In comparison, the benchmark MLP achieved 92.53% accuracy, 96.00% precision, 97.00% F1-score, 99.95% recall, and an AUC of 87.00%. This highlights the effectiveness of L2 regularization in improving predictive capabilities and model generalization for unseen instances.http://www.sciencedirect.com/science/article/pii/S2666764924000560Domain name systemDNS tunnelingMultilayered perceptronL2 regularizationMultilabel classification
spellingShingle Emmanuel Oluwatobi Asani
Mojiire Oluwaseun Ayoola
Emmanuel Tunbosun Aderemi
Victoria Oluwaseyi Adedayo-Ajayi
Joyce A. Ayoola
Oluwatobi Noah Akande
Jide Kehinde Adeniyi
Oluwambo Tolulope Olowe
L2R-MLP: a multilabel classification scheme for the detection of DNS tunneling
Data Science and Management
Domain name system
DNS tunneling
Multilayered perceptron
L2 regularization
Multilabel classification
title L2R-MLP: a multilabel classification scheme for the detection of DNS tunneling
title_full L2R-MLP: a multilabel classification scheme for the detection of DNS tunneling
title_fullStr L2R-MLP: a multilabel classification scheme for the detection of DNS tunneling
title_full_unstemmed L2R-MLP: a multilabel classification scheme for the detection of DNS tunneling
title_short L2R-MLP: a multilabel classification scheme for the detection of DNS tunneling
title_sort l2r mlp a multilabel classification scheme for the detection of dns tunneling
topic Domain name system
DNS tunneling
Multilayered perceptron
L2 regularization
Multilabel classification
url http://www.sciencedirect.com/science/article/pii/S2666764924000560
work_keys_str_mv AT emmanueloluwatobiasani l2rmlpamultilabelclassificationschemeforthedetectionofdnstunneling
AT mojiireoluwaseunayoola l2rmlpamultilabelclassificationschemeforthedetectionofdnstunneling
AT emmanueltunbosunaderemi l2rmlpamultilabelclassificationschemeforthedetectionofdnstunneling
AT victoriaoluwaseyiadedayoajayi l2rmlpamultilabelclassificationschemeforthedetectionofdnstunneling
AT joyceaayoola l2rmlpamultilabelclassificationschemeforthedetectionofdnstunneling
AT oluwatobinoahakande l2rmlpamultilabelclassificationschemeforthedetectionofdnstunneling
AT jidekehindeadeniyi l2rmlpamultilabelclassificationschemeforthedetectionofdnstunneling
AT oluwambotolulopeolowe l2rmlpamultilabelclassificationschemeforthedetectionofdnstunneling