DEVELOPMENT OF AN INTRUSION DETECTION SYSTEM USING ENSEMBLE MACHINE LEARNING

This study addresses the critical challenge of improving cybersecurity through enhanced intrusion detection by developing an ensemble machine learning-based Intrusion Detection System (IDS). As cyberattacks grow increasingly sophisticated, traditional IDS solutions— while valuable for monitoring network traffic and identifying vulnerabilities—often suffer from high false positive/negative rates and lack adaptability to evolving threats. This research proposes an advanced IDS model that leverages ensemble machine learning techniques to combine the strengths of multiple algorithms, thereby improving detection accuracy, reducing false alarms, and enabling real-time threat response. The study focuses on utilizing publicly available datasets to train and evaluate the model, targeting a broad range of cyber threats, including malware, Denial-of-Service (DoS) attacks, and unauthorized access attempts. By integrating deep learning and ensemble methods, the proposed system aims to overcome the limitations of single-model approaches, offering a more robust and adaptive solution for network security. The findings are expected to benefit sectors requiring high-security standards, such as healthcare, banking, and government, by providing a scalable, efficient, and automated intrusion detection framework. However, the study acknowledges limitations, including reliance on public datasets and a focus on network-based threats, excluding endpoint and insider threats. Ultimately, this research contributes to the advancement of intelligent cybersecurity systems capable of countering modern cyber threats with greater precision and speed