Improving Cloud Data Communication Security Through Intelligent Machine Learning Models

Abstract

Cloud computing has become an essential platform for data storage and communication due to its scalability, flexibility, and cost efficiency. However, the increasing volume of cloudbased data communication also raises significant security concerns, including unauthorized access, malicious attacks, and network intrusions. To address these challenges, this work proposes an intelligent machine learning–based framework for improving cloud data communication security. The proposed system analyzes network traffic attributes such as source IP, destination IP, protocol type, packet size, login time, country of origin, and risk score to detect potential attack patterns in cloud environments. Feature engineering techniques are applied to extract meaningful attributes from IP addresses, followed by preprocessing steps including label encoding and data normalization. Multiple machine learning algorithms, namely Random Forest, Gradient Boosting, and Extreme Gradient Boosting (XGBoost), are employed to classify and identify various types of cyber-attacks in cloud networks. The models are trained and evaluated using a cloud security dataset, and their performance is measured using metrics such as accuracy, classification report, and confusion matrix analysis. Among the implemented models, XGBoost demonstrates superior performance in predicting attack categories and identifying malicious activities. The proposed intelligent ML-based security framework enables early detection of suspicious network behavior and supports administrators in strengthening cloud communication security. This approach contributes to enhancing reliability, minimizing cyber threats, and improving the overall resilience of cloud computing environments.