Insider Threat Detection using Machine Learning Models for User Behavior Analysis

Insider threats pose a serious threat to an organization's security in the current digital environment. The emergence of Bring Your Own Device (BYOD) and Cloud Computing has made the protection of sensitive data critical. This work explored using machine learning (ML) models to analyze user behavior, with a focus on insider threat detection. The models employed state-of-the-art techniques such as anomaly detection, clustering, and deep learning to identify malicious activity initiated by authorized users. Further, the results demonstrated that these models can help organizations reduce insider risks and enhance cybersecurity protocols.