Cyber Threat's detection using Machine Learning Algorithms
Résumé
Cybercrime presents significant challenges to the security of data and computer systems. The security of data and computer systems has become an escalating concern with the growing utilization of the Internet in Burkina Faso. This article addresses these challenges by proposing a novel approach employing machine learning algorithms, including Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM), to enhance the detection and classification of cyber threats. We utilized three datasets containing text and URLs to explore various cyber threats such as phishing, cyberbullying, and online scams. The performance of our model, when compared to previous research, demonstrates promising results. Notably, the RF algorithm exhibited exceptional accuracy, achieving rates of 99.99% for cyberbullying, 99.4% for phishing, and 99.94% for online scams.
Fichier principal
Cyber Threat’s detection using Machine Learning Algorithms.pdf (345.39 Ko)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)