Intelligent SDN to enhance security in IoT networks

Software-defined networking (SDN) is a revolutionary technology that has revolutionised network management by providing flexibility and adaptability. As the popularity of SDN increases, it is crucial to address security vulnerabilities in these dynamic networks. This paper proposes a framework for e...

Full description

Saved in:
Bibliographic Details
Main Authors: Safi Ibrahim, Aya M. Youssef, Mahmoud Shoman, Sanaa Taha
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Egyptian Informatics Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110866524001270
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122163544784896
author Safi Ibrahim
Aya M. Youssef
Mahmoud Shoman
Sanaa Taha
author_facet Safi Ibrahim
Aya M. Youssef
Mahmoud Shoman
Sanaa Taha
author_sort Safi Ibrahim
collection DOAJ
description Software-defined networking (SDN) is a revolutionary technology that has revolutionised network management by providing flexibility and adaptability. As the popularity of SDN increases, it is crucial to address security vulnerabilities in these dynamic networks. This paper proposes a framework for enhancing security in SDN by utilising three separate Deep Learning models, namely Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM). This framework is utilised for the InSDN dataset, a huge dataset specifically created for SDN security research. The dataset consists of a total of 343,939 instances, encompassing both normal and attack traffic. The regular data yields a sum of 68,424, whereas the attack traffic comprises 275,515 occurrences. This study employs multiclassification algorithms to precisely detect and categorise diverse security threats in SDN. The InSDN dataset faces issues related to class imbalance, which are addressed by using the Synthetic Minority Over-sampling Technique (SMOTE). The SMOTE technique is utilised to create artificial instances of the underrepresented class, hence achieving a more equitable distribution of security hazards within the dataset. This strategy improves the efficacy of multiclassification techniques, ultimately resulting in greater accuracy in the identification and classification of different security threats in SDN environments. The initial DNN model exhibited satisfactory performance, with an accuracy of 87%. The second CNN model demonstrated strong and consistent performance, with an accuracy rate of 99%. In addition, an LSTM model attained a 90% accuracy rate.
format Article
id doaj-art-247cacbe4e194ee1a86b0422da9e3f9d
institution Kabale University
issn 1110-8665
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Egyptian Informatics Journal
spelling doaj-art-247cacbe4e194ee1a86b0422da9e3f9d2024-12-15T06:14:48ZengElsevierEgyptian Informatics Journal1110-86652024-12-0128100564Intelligent SDN to enhance security in IoT networksSafi Ibrahim0Aya M. Youssef1Mahmoud Shoman2Sanaa Taha3Dept. of Information Technology, Egyptian E-Learning University, EgyptDept. of Information Technology, Egyptian E-Learning University, Egypt; Corresponding author.Dept. of Information Technology, Egyptian E-Learning University, Egypt; Dept. of Information Technology, Faculty of Computers and Artificial Intelligence, Cairo University, EgyptDept. of Information Technology, Faculty of Computers and Artificial Intelligence, Cairo University, EgyptSoftware-defined networking (SDN) is a revolutionary technology that has revolutionised network management by providing flexibility and adaptability. As the popularity of SDN increases, it is crucial to address security vulnerabilities in these dynamic networks. This paper proposes a framework for enhancing security in SDN by utilising three separate Deep Learning models, namely Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM). This framework is utilised for the InSDN dataset, a huge dataset specifically created for SDN security research. The dataset consists of a total of 343,939 instances, encompassing both normal and attack traffic. The regular data yields a sum of 68,424, whereas the attack traffic comprises 275,515 occurrences. This study employs multiclassification algorithms to precisely detect and categorise diverse security threats in SDN. The InSDN dataset faces issues related to class imbalance, which are addressed by using the Synthetic Minority Over-sampling Technique (SMOTE). The SMOTE technique is utilised to create artificial instances of the underrepresented class, hence achieving a more equitable distribution of security hazards within the dataset. This strategy improves the efficacy of multiclassification techniques, ultimately resulting in greater accuracy in the identification and classification of different security threats in SDN environments. The initial DNN model exhibited satisfactory performance, with an accuracy of 87%. The second CNN model demonstrated strong and consistent performance, with an accuracy rate of 99%. In addition, an LSTM model attained a 90% accuracy rate.http://www.sciencedirect.com/science/article/pii/S1110866524001270Software-defined networkingSDNSecurityDL modelsInSDN datasetSMOTE
spellingShingle Safi Ibrahim
Aya M. Youssef
Mahmoud Shoman
Sanaa Taha
Intelligent SDN to enhance security in IoT networks
Egyptian Informatics Journal
Software-defined networking
SDN
Security
DL models
InSDN dataset
SMOTE
title Intelligent SDN to enhance security in IoT networks
title_full Intelligent SDN to enhance security in IoT networks
title_fullStr Intelligent SDN to enhance security in IoT networks
title_full_unstemmed Intelligent SDN to enhance security in IoT networks
title_short Intelligent SDN to enhance security in IoT networks
title_sort intelligent sdn to enhance security in iot networks
topic Software-defined networking
SDN
Security
DL models
InSDN dataset
SMOTE
url http://www.sciencedirect.com/science/article/pii/S1110866524001270
work_keys_str_mv AT safiibrahim intelligentsdntoenhancesecurityiniotnetworks
AT ayamyoussef intelligentsdntoenhancesecurityiniotnetworks
AT mahmoudshoman intelligentsdntoenhancesecurityiniotnetworks
AT sanaataha intelligentsdntoenhancesecurityiniotnetworks