Evaluating Machine Learning-based Security Frameworks for Public Cloud Data Protection

Abstract

The rapid adoption of cloud computing services has fundamentally transformed data management and storage within organizations. Public cloud computing offers numerous advantages, including cost efficiency, scalability, and accessibility. However, these benefits come with significant concerns regarding data security. As sensitive data increasingly migrates to public cloud environments, the potential risks associated with unauthorized access, data breaches, and other cyber threats become more pronounced. Traditional security measures often prove insufficient to address the dynamic and complex nature of threats in public cloud settings, driving interest in advanced technologies such as machine learning (ML) to enhance data security. This paper explores the challenges associated with data security in public cloud computing and proposes a solution framework based on machine learning. The proposed method demonstrates an accuracy of 97.6%, a mean absolute error (MAE) of 0.403, and a root mean square error (RMSE) of 0.203. Various machine learning models and techniques are integrated into comprehensive security architecture capable of adapting to evolving threats and providing robust data security. The effectiveness of the proposed solution is evaluated through a series of experiments and case studies. The findings highlight the potential of machine learning in transforming data security practices in public cloud computing. As organizations continue to rely on cloud services, adopting advanced security measures will be critical to ensuring the confidentiality, integrity, and availability of their data. This paper contributes to the growing body of knowledge on cloud security and provides a foundation for future research and development in this domain.