A Quantum Machine Learning Framework for Early Cyber Threat Detection in Cloud Computing Environments

Abstract

The rapid growth of cloud computing has introduced increasingly sophisticated cyber threats that challenge conventional security mechanisms. While classical machine learning techniques have demonstrated promising intrusion detection capabilities, their performance often deteriorates when processing massive and high-dimensional security datasets. This paper proposes a Quantum Machine Learning (QML)-based cyber threat detection framework that integrates quantum feature mapping with hybrid quantum-classical neural networks for real-time attack identification. The proposed architecture leverages quantum kernels for efficient feature representation while employing deep neural classifiers for threat categorization. Experimental evaluation on benchmark cloud security datasets demonstrates improvements in detection accuracy, computational efficiency, and false-positive reduction compared to traditional machine learning models. The proposed framework provides a scalable solution for next-generation cloud security by exploiting the computational advantages of quantum computing for intelligent cybersecurity applications.