As the number of cyber threats and attacks increases, there is a growing demand for network attack analysis today. Due to the scalability and adaptability of its internet-based computing resources, cloud computing is favoured by businesses around the globe. Protecting hosts, organisations, and data from increasingly sophisticated digital threats is a top priority for scientists, who are focusing more and more on the security of cloud data. Over the past couple of decades, researchers have experimented with the framework for Intrusion Detection (ID), resulting in a plethora of methodologies. In the future, however, these methods will not be sufficient for the intrusion detection framework. The objective of this research is to employ ensemble model of Effective gradient boosting decision tree (EGDT-boost) performs a classification to determine whether or not an interruption in a framework has occurred. This model created an ensemble classifier using an Decision tree and a Gradiant Boosting classifier. The gradient boosting methods improve the performance of the Decision Tree classifier by reducing the number of detected errors. This article examines the proposed classifier and compares it to established various classification techniques. In terms of Precision, Recall, F-Measure, and Accuracy, the proposed model produces superior results compared to existing methods