Fatima Zohra Allam

Enterprise networks, as the backbone of modern information systems, are increasingly exposed to sophisticated and rapidly evolving cyber threats. Traditional Intrusion Detection Systems (IDS), based on static attack signatures, often fail to detect novel or complex intrusions, resulting in high false alarm rates. This study proposes an intelligent IDS that leverages Machine Learning and Deep Learning techniques to significantly improve detection accuracy and reduce alert noise. The system is capable of classifying attacks by severity and provides an intuitive interface to support efficient threat monitoring. Beyond technical performance, the solution addresses managerial objectives by lowering maintenance costs, enhancing service quality, accelerating incident response, and ensuring high availability with straightforward deployment. The proposed model offers a scalable and resilient IDS tailored for enterprise environments, contributing both practical and strategic value in the fight against increasingly sophisticated cyberattacks.