Article Type
Article
Abstract
A misuse attack is the most common and dangerous type of attack that could target NFV (Network Function Virtualization). In a misuse attack, the attacker attempts to consume the NVF environment’s resources by sending a large amount of traffic. To protect the NFV environment, an early and accurate misuse attack detection system has been proposed based on NFV and Random Forest Classifier. The proposed model starts with importing the dataset and analyzing it then pre-processing and feature selection using a PSO (particle swarm optimization) Test algorithm, classification is based on the most common and efficient machine learning technique, which is Random Forest and Niave Bayse used. Finally, in order to test and evaluate the performance of the proposed model, the KDD (knowledge discovery in databases) dataset is utilized. The proposed system outperformed the most comparable previous research in terms of performance, as indicated by the results, achieving an accuracy rate of 99.98% for Random Forest and 99.5% for Niave Bayse.
Keywords
Network Function Virtualization (NFV), Machine learning ML, Random forest (RF), Niave Bayse, PSO test algorithm, KDD
Recommended Citation
Taha, Mustafa H.; Hawi, Ibtesam Jomaa; and Ali, Wafaa Waheeb Abdullah
(2025)
"Protection the NFV Net-Work Using the Random Forest Classification,"
Al-Esraa University College Journal for Engineering Sciences: Vol. 7:
Iss.
11, Article 6.
DOI: https://doi.org/10.70080/2790-7732.1061
Included in
Biomedical Engineering and Bioengineering Commons, Chemical Engineering Commons, Civil and Environmental Engineering Commons, Computer Engineering Commons, Materials Science and Engineering Commons, Mechanical Engineering Commons