Intrusion Detection using Random Forest and Gradient Boosting Algorithm

Unauthorized device access remains a persistent and pressing concern in today’s interconnected world, posing significant security threats to sensitive information across various domains, including corporate networks, personal devices, and secure facilities. In response to this ever-present challenge, this research paper introduces an innovative and robust Unauthorized Device Access Detection System (UDADDS) that incorporates two-factor password authentication and face detection as a means to augment existing access control mechanisms. Moreover, the system leverages machine learning algorithms, specifically Random Forest and Gradient Boosting, for intrusion detection, shedding light on the advantages of the latter over the former. This paper aims to distinguish between these two algorithms, highlighting their distinctive characteristics and shedding light on real-life examples that illustrate how Gradient Boosting surpasses Random Forest in terms of efficiency and effectiveness in detecting unauthorized access attempts.