A Comprehensive IDs to Detect Botnet Attacks Using Machine Learning Techniques
Abdullah Alghamdi, Ayad F. Barsoum · 2024
In the contemporary landscape of cyber threats, Botnet attacks emerge as a pervasive and evolving menace, demanding sophisticated countermeasures. This paper presents a comprehensive development of an Intrusion Detection System (IDS) utilizing advanced machine learning techniques to thwart Botnet intrusions. Central to this IDS is an ensemble voting classifier, a synergistic integration of multiple algorithms, tailored to augment detection efficacy and adaptability. The paper delineates the systematic progression of our work, encompassing meticulous data preprocessing, strategic feature selection, rigorous model training, and the deployment of an intuitive web application. Evaluative measures are employed on real-time network traffic datasets, affirming the model's proficiency in discerning Botnet activities with notable accuracy and reliability. Our work introduces an approach to Botnet detection leveraging machine learning which increases the detection accuracy underscoring the efficacy of the proposed approach.