Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion Detection

With the rapid advancement of network technologies, cyberthreats have become increasingly sophisticated, posing significant challenges to traditional intrusion detection systems. Conventional machine learning and deep learning approaches frequently experience performance degradation when confronted...

Full description

Saved in:
Bibliographic Details
Main Authors: Sunghyuk Lee, Donghwan Roh, Jaehak Yu, Daesung Moon, Jonghyuk Lee, Ji-Hoon Bae
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/9/4851
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312724268351488
author Sunghyuk Lee
Donghwan Roh
Jaehak Yu
Daesung Moon
Jonghyuk Lee
Ji-Hoon Bae
author_facet Sunghyuk Lee
Donghwan Roh
Jaehak Yu
Daesung Moon
Jonghyuk Lee
Ji-Hoon Bae
author_sort Sunghyuk Lee
collection DOAJ
description With the rapid advancement of network technologies, cyberthreats have become increasingly sophisticated, posing significant challenges to traditional intrusion detection systems. Conventional machine learning and deep learning approaches frequently experience performance degradation when confronted with imbalanced datasets and novel attack vectors. To address these limitations, this study proposes a deep learning-based intrusion detection framework that employs feature fusion through incremental transfer learning between source and target domains. The proposed architecture integrates convolutional neural networks (CNNs) with an attention mechanism to extract and aggregate salient features, thereby enhancing the model’s discriminative capacity between normal traffic and various network attack categories. Experimental results demonstrate that the proposed model achieves a detection accuracy of 94.21% even when trained on only 33% of the available data, outperforming conventional models. These findings underscore the effectiveness of the proposed feature fusion strategy via transfer learning in improving detection capabilities within dynamic and evolving cyberthreat environments.
format Article
id doaj-art-99ce88a9fce44a058f4b0810a09525df
institution Kabale University
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-99ce88a9fce44a058f4b0810a09525df2025-08-20T03:52:57ZengMDPI AGApplied Sciences2076-34172025-04-01159485110.3390/app15094851Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion DetectionSunghyuk Lee0Donghwan Roh1Jaehak Yu2Daesung Moon3Jonghyuk Lee4Ji-Hoon Bae5Department of AI and Big Data Engineering, Daegu Catholic University, Gyeongsan-si 38430, Republic of KoreaDepartment of AI and Big Data Engineering, Daegu Catholic University, Gyeongsan-si 38430, Republic of KoreaElectronics and Telecommunications Research Institute, Daejeon 34129, Republic of KoreaElectronics and Telecommunications Research Institute, Daejeon 34129, Republic of KoreaDepartment of AI and Big Data Engineering, Daegu Catholic University, Gyeongsan-si 38430, Republic of KoreaDepartment of Computer Education, Korea National University of Education, Cheongju-si 28173, Republic of KoreaWith the rapid advancement of network technologies, cyberthreats have become increasingly sophisticated, posing significant challenges to traditional intrusion detection systems. Conventional machine learning and deep learning approaches frequently experience performance degradation when confronted with imbalanced datasets and novel attack vectors. To address these limitations, this study proposes a deep learning-based intrusion detection framework that employs feature fusion through incremental transfer learning between source and target domains. The proposed architecture integrates convolutional neural networks (CNNs) with an attention mechanism to extract and aggregate salient features, thereby enhancing the model’s discriminative capacity between normal traffic and various network attack categories. Experimental results demonstrate that the proposed model achieves a detection accuracy of 94.21% even when trained on only 33% of the available data, outperforming conventional models. These findings underscore the effectiveness of the proposed feature fusion strategy via transfer learning in improving detection capabilities within dynamic and evolving cyberthreat environments.https://www.mdpi.com/2076-3417/15/9/4851network intrusion detectiontransfer learningdeep learningfeature fusion
spellingShingle Sunghyuk Lee
Donghwan Roh
Jaehak Yu
Daesung Moon
Jonghyuk Lee
Ji-Hoon Bae
Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion Detection
Applied Sciences
network intrusion detection
transfer learning
deep learning
feature fusion
title Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion Detection
title_full Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion Detection
title_fullStr Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion Detection
title_full_unstemmed Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion Detection
title_short Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion Detection
title_sort deep feature fusion via transfer learning for multi class network intrusion detection
topic network intrusion detection
transfer learning
deep learning
feature fusion
url https://www.mdpi.com/2076-3417/15/9/4851
work_keys_str_mv AT sunghyuklee deepfeaturefusionviatransferlearningformulticlassnetworkintrusiondetection
AT donghwanroh deepfeaturefusionviatransferlearningformulticlassnetworkintrusiondetection
AT jaehakyu deepfeaturefusionviatransferlearningformulticlassnetworkintrusiondetection
AT daesungmoon deepfeaturefusionviatransferlearningformulticlassnetworkintrusiondetection
AT jonghyuklee deepfeaturefusionviatransferlearningformulticlassnetworkintrusiondetection
AT jihoonbae deepfeaturefusionviatransferlearningformulticlassnetworkintrusiondetection