A STUDY ON THE DETECTION AND PREVENTION OF CYBER ATTACKS USING MACHINE LEARNING ALGORITHMS

Abstract

This study explores the use of machine learning algorithms to detect and prevent cyberattacks. The research focuses on several widely used models, including Decision Trees, Support Vector Machines (SVM), Random Forests, and Neural Networks, evaluating their performance on datasets related to network traffic, intrusion detection, and malware classification. Preprocessing techniques such as data cleaning, feature selection, and balancing were applied to optimize the datasets for model training. The results show that Neural Networks outperformed the other algorithms in terms of accuracy, precision, recall, and F1-score, followed by Random Forests. This study highlights the importance of machine learning in cybersecurity, demonstrating its potential to detect complex attack patterns and improve real-time threat detection systems.