<![CDATA[Rapid cloud adoption has transformed enterprise IT infrastructures, but also introduces complex cybersecurity challenges due to the distributed and dynamic nature of cloud environments, increasing exposure to sophisticated cyber threats. This study aims to design and evaluate machine learning-based approaches to enhance cybersecurity in distributed cloud infrastructures, focusing on improving threat detection accuracy, scalability, and operational efficiency in multi-cloud environments. The proposed method employs a layered machine learning framework integrating supervised and unsupervised algorithms to detect intrusions, anomalous behaviors, and policy violations across distributed cloud nodes, supported by real-time data collection and adaptive model training. A methodological illustration indicates that machine learning approaches can achieve higher detection accuracy approximately 90% compared to traditional rule based systems approximately 78%, while reducing false-positive rates from around 22% to 10%, and experimental results further confirm improved detection performance, reduced false positives, and faster response times while maintaining scalability under increasing workloads. These findings demon- strate that machine learning-driven cybersecurity solutions provide a more adaptive, scalable, and effective defense mechanism, supporting secure and sustainable digital transformation in modern cloud environments.]]>
Copyrights © 2026
