A Comparative Analysis of Single and Multi-View Deep Learning for Cybersecurity Anomaly Detection

This paper investigates the application of Deep Multi-View Learning (DMVL) to enhance the responsiveness of intrusion detection systems (IDS) in modern network environments, addressing the limitations of traditional IDS. The study used diverse datasets, including TON_IoT and UNSW-NB15, to evaluate a...

Full description

Saved in:
Bibliographic Details
Main Authors: Min Li, Yuansong Qiao, Brian Lee
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10975758/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849328744543551488
author Min Li
Yuansong Qiao
Brian Lee
author_facet Min Li
Yuansong Qiao
Brian Lee
author_sort Min Li
collection DOAJ
description This paper investigates the application of Deep Multi-View Learning (DMVL) to enhance the responsiveness of intrusion detection systems (IDS) in modern network environments, addressing the limitations of traditional IDS. The study used diverse datasets, including TON_IoT and UNSW-NB15, to evaluate anomaly detection capabilities across various host and network scenarios, with a particular emphasis on dataset diversity, single model diversity, and multi-view models diversity. The experiment found that multi-view models based on Autoencoder (AE) and Convolutional Neural Network (CNN) performed better in general than the corresponding single view model in detection anomaly. However, certain single view models outperformed multi-view models like Deep Generalized Canonical Correlation Analysis (DGCCA) in specific cases, This result showed that although multi-view methods generally had stronger comprehensive analysis capabilities, they were not the best choice in all scenarios. The effectiveness of multi-view methods depended largely on the specific model design and data characteristics. Further investigations comparing multi-view models, such as multi-view AE, CNN, and DGCCA, showed that the multi-view CNN model not only achieved the highest F1 score on the TON_IoT dataset, but also demonstrated strong robustness on the UNSW-NB15 dataset. These findings confirmed the effectiveness of multi-view methods in integrating complementary data in host and enterprise network scenarios based on network environments.
format Article
id doaj-art-a74bc4dd301548a1b337427e40d53026
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a74bc4dd301548a1b337427e40d530262025-08-20T03:47:28ZengIEEEIEEE Access2169-35362025-01-0113839968401210.1109/ACCESS.2025.356406610975758A Comparative Analysis of Single and Multi-View Deep Learning for Cybersecurity Anomaly DetectionMin Li0https://orcid.org/0009-0005-0939-5680Yuansong Qiao1https://orcid.org/0000-0002-1543-1589Brian Lee2Software Research Institute, Technological University of the Shannon: Midlands Midwest, Athlone, IrelandSoftware Research Institute, Technological University of the Shannon: Midlands Midwest, Athlone, IrelandSoftware Research Institute, Technological University of the Shannon: Midlands Midwest, Athlone, IrelandThis paper investigates the application of Deep Multi-View Learning (DMVL) to enhance the responsiveness of intrusion detection systems (IDS) in modern network environments, addressing the limitations of traditional IDS. The study used diverse datasets, including TON_IoT and UNSW-NB15, to evaluate anomaly detection capabilities across various host and network scenarios, with a particular emphasis on dataset diversity, single model diversity, and multi-view models diversity. The experiment found that multi-view models based on Autoencoder (AE) and Convolutional Neural Network (CNN) performed better in general than the corresponding single view model in detection anomaly. However, certain single view models outperformed multi-view models like Deep Generalized Canonical Correlation Analysis (DGCCA) in specific cases, This result showed that although multi-view methods generally had stronger comprehensive analysis capabilities, they were not the best choice in all scenarios. The effectiveness of multi-view methods depended largely on the specific model design and data characteristics. Further investigations comparing multi-view models, such as multi-view AE, CNN, and DGCCA, showed that the multi-view CNN model not only achieved the highest F1 score on the TON_IoT dataset, but also demonstrated strong robustness on the UNSW-NB15 dataset. These findings confirmed the effectiveness of multi-view methods in integrating complementary data in host and enterprise network scenarios based on network environments.https://ieeexplore.ieee.org/document/10975758/Deep multi-view learning (DMVL)anomaly detectionenterprise network intrusion detection
spellingShingle Min Li
Yuansong Qiao
Brian Lee
A Comparative Analysis of Single and Multi-View Deep Learning for Cybersecurity Anomaly Detection
IEEE Access
Deep multi-view learning (DMVL)
anomaly detection
enterprise network intrusion detection
title A Comparative Analysis of Single and Multi-View Deep Learning for Cybersecurity Anomaly Detection
title_full A Comparative Analysis of Single and Multi-View Deep Learning for Cybersecurity Anomaly Detection
title_fullStr A Comparative Analysis of Single and Multi-View Deep Learning for Cybersecurity Anomaly Detection
title_full_unstemmed A Comparative Analysis of Single and Multi-View Deep Learning for Cybersecurity Anomaly Detection
title_short A Comparative Analysis of Single and Multi-View Deep Learning for Cybersecurity Anomaly Detection
title_sort comparative analysis of single and multi view deep learning for cybersecurity anomaly detection
topic Deep multi-view learning (DMVL)
anomaly detection
enterprise network intrusion detection
url https://ieeexplore.ieee.org/document/10975758/
work_keys_str_mv AT minli acomparativeanalysisofsingleandmultiviewdeeplearningforcybersecurityanomalydetection
AT yuansongqiao acomparativeanalysisofsingleandmultiviewdeeplearningforcybersecurityanomalydetection
AT brianlee acomparativeanalysisofsingleandmultiviewdeeplearningforcybersecurityanomalydetection
AT minli comparativeanalysisofsingleandmultiviewdeeplearningforcybersecurityanomalydetection
AT yuansongqiao comparativeanalysisofsingleandmultiviewdeeplearningforcybersecurityanomalydetection
AT brianlee comparativeanalysisofsingleandmultiviewdeeplearningforcybersecurityanomalydetection