Generative Adversarial and Transformer Network Synergy for Robust Intrusion Detection in IoT Environments

Intrusion detection in the Internet of Things (IoT) environments is increasingly critical due to the rapid proliferation of connected devices and the growing sophistication of cyber threats. Traditional detection methods often fall short in identifying multi-class attacks, particularly in the presen...

Full description

Saved in:
Bibliographic Details
Main Authors: Pardis Sadatian Moghaddam, Ali Vaziri, Sarvenaz Sadat Khatami, Francisco Hernando-Gallego, Diego Martín
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/6/258
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849431900945383424
author Pardis Sadatian Moghaddam
Ali Vaziri
Sarvenaz Sadat Khatami
Francisco Hernando-Gallego
Diego Martín
author_facet Pardis Sadatian Moghaddam
Ali Vaziri
Sarvenaz Sadat Khatami
Francisco Hernando-Gallego
Diego Martín
author_sort Pardis Sadatian Moghaddam
collection DOAJ
description Intrusion detection in the Internet of Things (IoT) environments is increasingly critical due to the rapid proliferation of connected devices and the growing sophistication of cyber threats. Traditional detection methods often fall short in identifying multi-class attacks, particularly in the presence of high-dimensional and imbalanced IoT traffic. To address these challenges, this paper proposes a novel hybrid intrusion detection framework that integrates transformer networks with generative adversarial networks (GANs), aiming to enhance both detection accuracy and robustness. In the proposed architecture, the transformer component effectively models temporal and contextual dependencies within traffic sequences, while the GAN component generates synthetic data to improve feature diversity and mitigate class imbalance. Additionally, an improved non-dominated sorting biogeography-based optimization (INSBBO) algorithm is employed to fine-tune the hyper-parameters of the hybrid model, further enhancing learning stability and detection performance. The model is trained and evaluated on the CIC-IoT-2023 and TON_IoT dataset, which contains a diverse range of real-world IoT traffic and attack scenarios. Experimental results show that our hybrid framework consistently outperforms baseline methods, in both binary and multi-class intrusion detection tasks. The transformer-GAN achieves a multi-class classification accuracy of 99.67%, with an F1-score of 99.61%, and an area under the curve (AUC) of 99.80% in the CIC-IoT-2023 dataset, and achieves 98.84% accuracy, 98.79% F1-score, and 99.12% AUC on the TON_IoT dataset. The superiority of the proposed model was further validated through statistically significant <i>t</i>-test results, lower execution time compared to baselines, and minimal standard deviation across runs, indicating both efficiency and stability. The proposed framework offers a promising approach for enhancing the security and resilience of next-generation IoT systems.
format Article
id doaj-art-29c097e5d65840be988360903be7c021
institution Kabale University
issn 1999-5903
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-29c097e5d65840be988360903be7c0212025-08-20T03:27:29ZengMDPI AGFuture Internet1999-59032025-06-0117625810.3390/fi17060258Generative Adversarial and Transformer Network Synergy for Robust Intrusion Detection in IoT EnvironmentsPardis Sadatian Moghaddam0Ali Vaziri1Sarvenaz Sadat Khatami2Francisco Hernando-Gallego3Diego Martín4Department of Computer Science, Georgia State University, Atlanta, GA 30302, USADepartment of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ 07030, USADepartment of Data Science Engineering, University of Houston, Houston, TX 77204, USADepartment of Computer Science, Escuela de Ingeniería Informática de Segovia, Universidad de Valladolid, 40005 Segovia, SpainDepartment of Computer Science, Escuela de Ingeniería Informática de Segovia, Universidad de Valladolid, 40005 Segovia, SpainIntrusion detection in the Internet of Things (IoT) environments is increasingly critical due to the rapid proliferation of connected devices and the growing sophistication of cyber threats. Traditional detection methods often fall short in identifying multi-class attacks, particularly in the presence of high-dimensional and imbalanced IoT traffic. To address these challenges, this paper proposes a novel hybrid intrusion detection framework that integrates transformer networks with generative adversarial networks (GANs), aiming to enhance both detection accuracy and robustness. In the proposed architecture, the transformer component effectively models temporal and contextual dependencies within traffic sequences, while the GAN component generates synthetic data to improve feature diversity and mitigate class imbalance. Additionally, an improved non-dominated sorting biogeography-based optimization (INSBBO) algorithm is employed to fine-tune the hyper-parameters of the hybrid model, further enhancing learning stability and detection performance. The model is trained and evaluated on the CIC-IoT-2023 and TON_IoT dataset, which contains a diverse range of real-world IoT traffic and attack scenarios. Experimental results show that our hybrid framework consistently outperforms baseline methods, in both binary and multi-class intrusion detection tasks. The transformer-GAN achieves a multi-class classification accuracy of 99.67%, with an F1-score of 99.61%, and an area under the curve (AUC) of 99.80% in the CIC-IoT-2023 dataset, and achieves 98.84% accuracy, 98.79% F1-score, and 99.12% AUC on the TON_IoT dataset. The superiority of the proposed model was further validated through statistically significant <i>t</i>-test results, lower execution time compared to baselines, and minimal standard deviation across runs, indicating both efficiency and stability. The proposed framework offers a promising approach for enhancing the security and resilience of next-generation IoT systems.https://www.mdpi.com/1999-5903/17/6/258intrusion detectionIoT networkstransformersgenerative adversarial networknon-dominated sorting biogeography-based optimization
spellingShingle Pardis Sadatian Moghaddam
Ali Vaziri
Sarvenaz Sadat Khatami
Francisco Hernando-Gallego
Diego Martín
Generative Adversarial and Transformer Network Synergy for Robust Intrusion Detection in IoT Environments
Future Internet
intrusion detection
IoT networks
transformers
generative adversarial network
non-dominated sorting biogeography-based optimization
title Generative Adversarial and Transformer Network Synergy for Robust Intrusion Detection in IoT Environments
title_full Generative Adversarial and Transformer Network Synergy for Robust Intrusion Detection in IoT Environments
title_fullStr Generative Adversarial and Transformer Network Synergy for Robust Intrusion Detection in IoT Environments
title_full_unstemmed Generative Adversarial and Transformer Network Synergy for Robust Intrusion Detection in IoT Environments
title_short Generative Adversarial and Transformer Network Synergy for Robust Intrusion Detection in IoT Environments
title_sort generative adversarial and transformer network synergy for robust intrusion detection in iot environments
topic intrusion detection
IoT networks
transformers
generative adversarial network
non-dominated sorting biogeography-based optimization
url https://www.mdpi.com/1999-5903/17/6/258
work_keys_str_mv AT pardissadatianmoghaddam generativeadversarialandtransformernetworksynergyforrobustintrusiondetectioniniotenvironments
AT alivaziri generativeadversarialandtransformernetworksynergyforrobustintrusiondetectioniniotenvironments
AT sarvenazsadatkhatami generativeadversarialandtransformernetworksynergyforrobustintrusiondetectioniniotenvironments
AT franciscohernandogallego generativeadversarialandtransformernetworksynergyforrobustintrusiondetectioniniotenvironments
AT diegomartin generativeadversarialandtransformernetworksynergyforrobustintrusiondetectioniniotenvironments