AI-Driven Cybersecurity Threat Detection Framework Using Machine Learning Techniques

This paper proposes an AI-driven cybersecurity threat detection framework designed to improve detection accuracy, scalability, and operational usability in modern cybersecurity environments. The framework integrates data preprocessing, feature engineering, machine learning-based detection, threat classification, automated response handling, and continuous monitoring within a unified architecture. The study evaluates the framework conceptually using benchmark datasets including NSL-KDD and UNSW-NB15, and compares the performance of multiple machine learning classifiers such as Decision Tree, Support Vector Machine, and Random Forest. The proposed framework demonstrates improved detection performance and reduced false positives compared with traditional standalone approaches. The research contributes toward the development of intelligent and adaptive cybersecurity architectures suitable for enterprise infrastructures and Security Operations Center (SOC) environments.