MACHINE LEARNING-BASED INTRUSION DETECTION FOR BIG DATA SECURITY IN CLOUD HEALTHCARE SYSTEMS

Abstract

This paper presents a big data-driven security framework for protecting cloud-based healthcare data using ma- chine learning-based intrusion detection. With the rapid adoption of cloud computing in healthcare, large volumes of sensitive pa- tient data are stored and processed in distributed environments, increasing the risk of cyber threats and unauthorized access. To address this challenge, the proposed system integrates big data analytics with machine learning techniques to detect and classify network intrusions in real time. The NSL-KDD benchmark dataset is used for model training and evaluation. Three machine learning algorithms—Random Forest, Support Vector Machine, and Logistic Regression—are implemented and compared using accuracy, precision, and recall metrics. Experimental results show that the Random Forest model achieved superior performance with detection accuracy exceeding 99 percent across multiple attack categories, including DoS, Probe, R2L, and U2R attacks. The proposed framework enhances the security, scalability, and reliability of cloud-based healthcare systems. This study demon- strates the effectiveness of combining big data analytics and machine learning for intelligent and proactive cybersecurity in healthcare cloud environments.