Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset

The rapid growth of Internet of Things (IoT) is expected to add billions of IoT devices connected to the Internet. These devices represent a vast attack surface for cyberattacks. For example, these IoT devices can be infected with botnets to enable Distributed Denial of Service (DDoS) attacks. Signa...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Abdalgawad, Nada (author)
مؤلفون آخرون: Sajun, Ali Reza (author), Kaddoura, Yara (author), Zualkernan, Imran (author), Aloul, Fadi (author)
التنسيق: article
منشور في: 2021
الموضوعات:
الوصول للمادة أونلاين:https://hdl.handle.net/11073/26231
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513437986455552
author Abdalgawad, Nada
author2 Sajun, Ali Reza
Kaddoura, Yara
Zualkernan, Imran
Aloul, Fadi
author2_role author
author
author
author
author_facet Abdalgawad, Nada
Sajun, Ali Reza
Kaddoura, Yara
Zualkernan, Imran
Aloul, Fadi
author_role author
dc.creator.none.fl_str_mv Abdalgawad, Nada
Sajun, Ali Reza
Kaddoura, Yara
Zualkernan, Imran
Aloul, Fadi
dc.date.none.fl_str_mv 2021-12-31
2025-07-24T05:29:33Z
2025-07-24T05:29:33Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Abdalgawad, N., Sajun, A., Kaddoura, Y., Zualkernan, I. A., & Aloul, F. (2022). Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset. IEEE Access, 10, 6430–6441. https://doi.org/10.1109/access.2021.3140015
2169-3536
https://hdl.handle.net/11073/26231
10.1109/access.2021.3140015
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv IEEE
dc.relation.none.fl_str_mv https://doi.org/10.1109/access.2021.3140015
dc.rights.none.fl_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.subject.none.fl_str_mv Adversarial autoencoders
Cyber security
Generative adversarial networks
Internet of Things
Intrusion detection systems
dc.title.none.fl_str_mv Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description The rapid growth of Internet of Things (IoT) is expected to add billions of IoT devices connected to the Internet. These devices represent a vast attack surface for cyberattacks. For example, these IoT devices can be infected with botnets to enable Distributed Denial of Service (DDoS) attacks. Signature-based intrusion detection systems are traditional countermeasures for such attacks. However, these methods rely on human experts and are time-consuming in terms of updates and may not exhaust all attack types especially zero-day attacks. Deep learning has shown some promise in intrusion detection. This paper shows that it is possible to use generative deep learning methods like Adversarial Autoencoders (AAE) and Bidirectional Generative Adversarial Networks (BiGAN) to detect intruders based on an analysis of the network data. The recently posted full IoT-23 dataset based on Somfy door lock, Philips Hue and Amazon Echo devices was used to train generative deep learning models to detect a variety of attacks like DDoS, and various botnets like Mirai, Okiruk and Torii. Over 1.8 million network flows were used to train the various models. The resulting generative models outperform traditional machine learning techniques like Random Forests. Both AAE and BiGAN-based models were able to achieve an F1-Score of 0.99. A BiGAN to detect unknown attacks was also trained to detect novel zero-day attacks with an F1-Score from 0.85 to 1.
format article
id aus_9913fc4d460a75bcd05088815cc55cee
identifier_str_mv Abdalgawad, N., Sajun, A., Kaddoura, Y., Zualkernan, I. A., & Aloul, F. (2022). Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset. IEEE Access, 10, 6430–6441. https://doi.org/10.1109/access.2021.3140015
2169-3536
10.1109/access.2021.3140015
language_invalid_str_mv en
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/26231
publishDate 2021
publisher.none.fl_str_mv IEEE
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
spelling Generative Deep Learning to Detect Cyberattacks for the IoT-23 DatasetAbdalgawad, NadaSajun, Ali RezaKaddoura, YaraZualkernan, ImranAloul, FadiAdversarial autoencodersCyber securityGenerative adversarial networksInternet of ThingsIntrusion detection systemsThe rapid growth of Internet of Things (IoT) is expected to add billions of IoT devices connected to the Internet. These devices represent a vast attack surface for cyberattacks. For example, these IoT devices can be infected with botnets to enable Distributed Denial of Service (DDoS) attacks. Signature-based intrusion detection systems are traditional countermeasures for such attacks. However, these methods rely on human experts and are time-consuming in terms of updates and may not exhaust all attack types especially zero-day attacks. Deep learning has shown some promise in intrusion detection. This paper shows that it is possible to use generative deep learning methods like Adversarial Autoencoders (AAE) and Bidirectional Generative Adversarial Networks (BiGAN) to detect intruders based on an analysis of the network data. The recently posted full IoT-23 dataset based on Somfy door lock, Philips Hue and Amazon Echo devices was used to train generative deep learning models to detect a variety of attacks like DDoS, and various botnets like Mirai, Okiruk and Torii. Over 1.8 million network flows were used to train the various models. The resulting generative models outperform traditional machine learning techniques like Random Forests. Both AAE and BiGAN-based models were able to achieve an F1-Score of 0.99. A BiGAN to detect unknown attacks was also trained to detect novel zero-day attacks with an F1-Score from 0.85 to 1.American University of SharjahIEEE2025-07-24T05:29:33Z2025-07-24T05:29:33Z2021-12-31Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfAbdalgawad, N., Sajun, A., Kaddoura, Y., Zualkernan, I. A., & Aloul, F. (2022). Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset. IEEE Access, 10, 6430–6441. https://doi.org/10.1109/access.2021.31400152169-3536https://hdl.handle.net/11073/2623110.1109/access.2021.3140015enhttps://doi.org/10.1109/access.2021.3140015Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/oai:repository.aus.edu:11073/262312025-07-24T14:59:17Z
spellingShingle Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
Abdalgawad, Nada
Adversarial autoencoders
Cyber security
Generative adversarial networks
Internet of Things
Intrusion detection systems
status_str publishedVersion
title Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
title_full Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
title_fullStr Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
title_full_unstemmed Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
title_short Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
title_sort Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset
topic Adversarial autoencoders
Cyber security
Generative adversarial networks
Internet of Things
Intrusion detection systems
url https://hdl.handle.net/11073/26231