Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT Environments
Networks within the Internet of Things (IoT) have some of the most targeted devices due to their lightweight design and the sensitive data exchanged through smart city networks. One way to protect a system from an attack is to use machine learning (ML)-based intrusion detection systems (IDSs), signi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/19/10951 |
_version_ | 1797576197417205760 |
---|---|
author | Saleh Alabdulwahab Young-Tak Kim Aria Seo Yunsik Son |
author_facet | Saleh Alabdulwahab Young-Tak Kim Aria Seo Yunsik Son |
author_sort | Saleh Alabdulwahab |
collection | DOAJ |
description | Networks within the Internet of Things (IoT) have some of the most targeted devices due to their lightweight design and the sensitive data exchanged through smart city networks. One way to protect a system from an attack is to use machine learning (ML)-based intrusion detection systems (IDSs), significantly improving classification tasks. Training ML algorithms require a large network traffic dataset; however, large storage and months of recording are required to capture the attacks, which is costly for IoT environments. This study proposes an ML pipeline using the conditional tabular generative adversarial network (CTGAN) model to generate a synthetic dataset. Then, the synthetic dataset was evaluated using several types of statistical and ML metrics. Using a decision tree, the accuracy of the generated dataset reached 0.99, and its lower complexity reached 0.05 s training and 0.004 s test times. The results show that synthetic data accurately reflect real data and are less complex, making them suitable for IoT environments and smart city applications. Thus, the generated synthetic dataset can further train models to secure IoT networks and applications. |
first_indexed | 2024-03-10T21:48:50Z |
format | Article |
id | doaj.art-a69a28b418e648ce8c1735712d74e34e |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T21:48:50Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-a69a28b418e648ce8c1735712d74e34e2023-11-19T14:06:29ZengMDPI AGApplied Sciences2076-34172023-10-0113191095110.3390/app131910951Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT EnvironmentsSaleh Alabdulwahab0Young-Tak Kim1Aria Seo2Yunsik Son3Department of Computer Science and Engineering, Dongguk University, Seoul 04620, Republic of KoreaDepartment of Biomedical Sciences, Korea University College of Medicine, Seoul 02841, Republic of KoreaDepartment of Computer Science and Engineering, Dongguk University, Seoul 04620, Republic of KoreaDepartment of Computer Science and Engineering, Dongguk University, Seoul 04620, Republic of KoreaNetworks within the Internet of Things (IoT) have some of the most targeted devices due to their lightweight design and the sensitive data exchanged through smart city networks. One way to protect a system from an attack is to use machine learning (ML)-based intrusion detection systems (IDSs), significantly improving classification tasks. Training ML algorithms require a large network traffic dataset; however, large storage and months of recording are required to capture the attacks, which is costly for IoT environments. This study proposes an ML pipeline using the conditional tabular generative adversarial network (CTGAN) model to generate a synthetic dataset. Then, the synthetic dataset was evaluated using several types of statistical and ML metrics. Using a decision tree, the accuracy of the generated dataset reached 0.99, and its lower complexity reached 0.05 s training and 0.004 s test times. The results show that synthetic data accurately reflect real data and are less complex, making them suitable for IoT environments and smart city applications. Thus, the generated synthetic dataset can further train models to secure IoT networks and applications.https://www.mdpi.com/2076-3417/13/19/10951intrusion detection systemmachine learninginformation securityIoTCTGANadvanced persistent threat |
spellingShingle | Saleh Alabdulwahab Young-Tak Kim Aria Seo Yunsik Son Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT Environments Applied Sciences intrusion detection system machine learning information security IoT CTGAN advanced persistent threat |
title | Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT Environments |
title_full | Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT Environments |
title_fullStr | Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT Environments |
title_full_unstemmed | Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT Environments |
title_short | Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT Environments |
title_sort | generating synthetic dataset for ml based ids using ctgan and feature selection to protect smart iot environments |
topic | intrusion detection system machine learning information security IoT CTGAN advanced persistent threat |
url | https://www.mdpi.com/2076-3417/13/19/10951 |
work_keys_str_mv | AT salehalabdulwahab generatingsyntheticdatasetformlbasedidsusingctganandfeatureselectiontoprotectsmartiotenvironments AT youngtakkim generatingsyntheticdatasetformlbasedidsusingctganandfeatureselectiontoprotectsmartiotenvironments AT ariaseo generatingsyntheticdatasetformlbasedidsusingctganandfeatureselectiontoprotectsmartiotenvironments AT yunsikson generatingsyntheticdatasetformlbasedidsusingctganandfeatureselectiontoprotectsmartiotenvironments |