On-demand storage, data management, processing power, applications, and other cloud computing features are abundant. Using these tools is easy. Access is easy. Using machine learning-based intrusion detection systems improves cloud security. The main objectives include tracking and evaluating cloud resources, services, and networks to identify and thwart cyber attacks. Intrusion detection models primarily use machine learning, specifically the Random Forest (RF) approach. Random Forest uses many decision trees to improve prediction accuracy. Feature engineering defines model development. It involves selecting and maximizing features of a dataset for a machine learning model. Good feature engineering allows the model to detect attacks and identify trends. This model can be used to track cloud resources, services, and networks to enhance cloud security. This application uses machine learning techniques to detect anomalous trends in cyber attacks and enhance the security of cloud infrastructure. Two data sets, NSL-KDD and Bot-IoT, support the concept. These attack detection datasets are standard. The attack detection accuracy of this model is higher than the current experiments, demonstrating its reliability in identifying security vulnerabilities. To improve cloud detection, the voting classifier and the stacking classifier achieved 99% and 100% accuracy on KDD-Cup and BOT-IoT data, respectively.