Threat Behaviour Analytics for Cloud Security using Machine Learning

Authors: Deshmukh Jay Rajesh, Gangurde Pawan Rajaram, Raut Kartik Ganesh, Shankhpal Meghraj Vijay, Mahesh Dhande

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: Cloud computing has become an essential platform for storing and managing large volumes of sensitive data, making it a prime target for cyber-attacks. Traditional security mechanisms often fail to detect complex and evolving threats in real time. This paper presents an intelligent cloud security system based on threat behavior analytics using a hybrid machine learning approach. The proposed system analyzes cloud log data, including user activities, system events, and network transactions, to identify suspicious patterns and potential cyber-attacks. A hybrid model combining Random Forest and Support Vector Machine (SVM) is implemented to improve detection accuracy and reduce false alerts. The system also provides preventive suggestions and generates detailed reports to assist administrators in understanding and mitigating threats. A web-based interface is developed to enable easy interaction, allowing users to input data and monitor security status efficiently. The proposed solution aims to enhance cloud security by providing accurate, reliable, and real-time attack detection. Experimental results demonstrate that the system achieves high accuracy and efficiency, making it suitable for modern cloud environments.

Keywords: Cloud Security, Threat Detection, Machine Learning, Random Forest, Support Vector Machine (SVM), Hybrid Model, Cloud Log Analysis, Cyber Attack Detection, Anomaly Detection, Web-Based Security System.

Paper Id: 233087

Published On: 2026-04-30

Published In: Volume 14, Issue 2, March-April 2026

Share this