Cyberattack Analysis, Detection and Prevention using Machine Learning

Abstract: In today's linked world, with the increase of cyberattacks, it is critical to have strong detection and prevention systems. This study presents an advanced approach utilizing both machine learning and deep learning algorithms for cyberattack detection and prevention. The UNSW-NB15 dataset, renowned for its comprehensive representation of diverse cyber threats, serves as the foundation for experimentation and evaluation. Several algorithms such as Random Forest, Naïve Bayes, boosting algorithms, Artificial neural networks, Support vector machine are employed where the comparative analysis focuses on evaluating the efficiency of each algorithm in terms of recall, precision, and accuracy metrics. This study enhances the development of cybersecurity defense tactics by offering valuable perspectives on the efficacy of different machine learning methods in predicting cyberattacks. Experimental findings indicate that the boosting algorithm strategy is capable of identifying and preventing cyber threats with an accuracy rate of 94%.