dc.contributor.author |
Alomiri, Abdullah |
|
dc.contributor.author |
Mishra, Shailendra |
|
dc.contributor.author |
AlShehri, Mohammed |
|
dc.date.accessioned |
2023-07-24T06:01:24Z |
|
dc.date.available |
2023-07-24T06:01:24Z |
|
dc.date.issued |
2023-07-24 |
|
dc.identifier.issn |
2210-142X |
|
dc.identifier.uri |
https://journal.uob.edu.bh:443/handle/123456789/5154 |
|
dc.description.abstract |
The increasing prevalence of Internet of Things (IoT) systems has brought about significant security concerns. Cyber-attacks,
including denial-of-service attacks, malware infections, and phishing attempts, pose serious threats to the integrity and functionality
of IoT networks. To ensure comprehensive protection, it is essential to develop machine learning-based security measures that employ
robust models and integrate multiple security mechanisms. In this study, a Ridge Classifier is utilized as a powerful model to detect
anomalies in IoT systems. By leveraging this approach, the proposed security system can accurately identify and predict cyber-attacks
in real-time, utilizing secure and up-to-date information from the network. The integration of machine learning techniques enhances the
system’s ability to detect and mitigate threats effectively. Experimental results demonstrate the high accuracy of the proposed system in
detecting and mitigating network threats in IoT systems, achieving a remarkable accuracy rate of 97 percent. This level of accuracy not
only improves the security and resilience of government and business networks but also ensures the protection of valuable data from
malicious threats. The development of machine learning-based security measures, such as the system presented in this study, is crucial
for addressing the security challenges faced by IoT systems. By accurately detecting and predicting cyber-attacks, these measures play a
pivotal role in safeguarding the integrity, confidentiality, and availability of IoT networks. Furthermore, the integration of robust models
and the incorporation of multiple security measures provide a comprehensive defense against a wide range of threats. In conclusion, the
implementation of machine learning-based security measures, particularly utilizing the Ridge Classifier model, offers significant benefits
in protecting IoT systems. By effectively detecting and mitigating network threats with high accuracy, these measures contribute to
improving the security and resilience of government and business networks. Moreover, the protection of data from malicious threats
ensures the integrity and confidentiality of IoT systems, fostering trust and reliability in the rapidly expanding IoT landscape. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
University of Bahrain |
en_US |
dc.subject |
Cyber Attacks |
en_US |
dc.subject |
Network Threats |
en_US |
dc.subject |
Network Security |
en_US |
dc.subject |
Security Countermeasure |
en_US |
dc.title |
Machine learning-based security mechanism to detect and prevent cyber-attack in IoT networks |
en_US |
dc.identifier.doi |
https://dx.doi.org/10.12785/ijcds/160148 |
|
dc.volume |
16 |
en_US |
dc.issue |
1 |
en_US |
dc.pagestart |
645 |
en_US |
dc.pageend |
659 |
en_US |
dc.contributor.authorcountry |
Saudi Arabia |
en_US |
dc.contributor.authorcountry |
Saudi Arabia |
|
dc.contributor.authorcountry |
Saudi Arabia |
|
dc.contributor.authoraffiliation |
Department of Information Technology, College of Computer and Information Sciences, Majmaah University |
en_US |
dc.contributor.authoraffiliation |
Department of Information Technology, College of Computer and Information Sciences, Majmaah University |
|
dc.contributor.authoraffiliation |
Department of Information Technology, College of Computer and Information Sciences, Majmaah University |
|
dc.source.title |
International Journal of Computing and Digital Systems |
en_US |
dc.abbreviatedsourcetitle |
IJCDS |
en_US |