Privilege escalation attacks in cloud environments pose a significant threat to the integrity and confidentiality of sensitive data. These attacks enable unauthorized users to gain elevated access privileges, thereby jeopardizing organizational security. Historically, such threats were addressed using manual monitoring and rule-based systems that relied on predefined thresholds and basic anomaly detection methods. However, these traditional approaches have proven both time-consuming and prone to high false-positive rates, especially when applied to large, dynamic datasets. Recent advances in machine learning have reshaped the landscape of cloud security, offering automated, adaptive, and scalable solutions for detecting privilege escalation. By leveraging algorithms such as Random Forest, AdaBoost, XGBoost, LightGBM, and CatBoost, the proposed system continually refines its detection capabilities based on historical attack data, thereby reducing false positives and improving realtime responsiveness. Experimental results suggest that this machinelearning-driven framework significantly outperforms traditional rulebased methods in detecting subtle indicators of privilege escalation, ultimately providing more robust protection against evolving attack techniques. In this research, we propose a comprehensive solution that harnesses these advanced algorithms to secure complex cloud environments from privilege escalation attacks. Our findings underscore the transformative potential of machine learning in cloud security, offering organizations an automated, proactive, and highly accurate defense mechanism. By demonstrating improved scalability, adaptability, and precision, this system lays the groundwork for more effective threat detection and mitigation in modern cloud infrastructures.