Significant changes in enterprise digital infrastruc-tures include scalable, flexible, and cost-effective computing services via cloud computing platforms. The Google Cloud Platform has become one of the most popular cloud ecosystems that is being used by enterprises to host enterprise applications, distributed workloads, and large data storage services. Due to the increased complexity associated with modern cloud infrastruc-tures, there are now many more types of cybersecurity issues such as misconfigurations of cloud services, identity theft, insecure application programming interfaces (APIs), unauthorized access, and new cyber threats associated with cloud services. The need for a Cloud Security Posture Management (CSPM) system has grown considerably as CSPM systems provide orga-nizations with the ability to identify and address security risks by providing continuous visibility into their cloud environments. Traditional CSPM systems are largely reliant on static rule-based analysis and established compliance methodologies; therefore, they are not well suited to identify new or evolving threats or attack patterns in today’s complex cloud infrastructures. This research addresses the design of an artificial intelli-gence (AI)-based predictive Cloud Security Posture Management (CSPM) architecture for Google Cloud Platform. This architec-ture incorporates AI, behavioral analysis, and predictive threat intelligence to provide continuous monitoring of cloud data and usage, provide early identification of security anomalies, and predict potential security risks prior to an organization suffering an operational compromise. The effectiveness of the AI predictive CSPM architecture is evaluated in several cloud security scenarios. Examples of these scenarios include cloud misconfigurations, unusual access activity, suspicious API calls, and privilege escalation attempts. The results of the study indicate that using AI-based predictive mon-itoring provides organizations substantially better cloud security posture visibility, more accurate prediction and identification of threats, and ultimately, provides organizations with a greater response ability than typical CSPM architectures. The results of this study demonstrate the need for intelligent and predictive cybersecurity systems to support cloud-native infrastructures. [1], [2].

The AI-based predictive CSPM framework for Google Cloud Platform environments, developed and validated as part this project, unweighted the integration of AI, real-time behavioural monitoring, predictive threat intelligence and anomaly-based operational analytics into an improved method for managing proactive cyber security within cloud environments. The experimental evaluation has demonstrated that predic-tive behavioural analysis provides significant improvements in the operational visibility, and threat identification capabil-ity of cloud operational environments when compared with traditional static CSPM solutions. The analytical engine has successfully predicted a number of malicious behaviours within Google Cloud, such as suspicious cloud activities, authentication anomalies, abnormal API interactions, irregular workload communication and instances of privilege escalation prior to actual operational compromise. The comparative analysis has reaffirmed that predictive cyber security intelligence, provides a basis for enhanced operational resilience, and enhanced capability for proactive risk management within highly dynamic cloud-native infras-tructures such as Google Cloud. The ability of the predictive CSPM framework to adaptively learn from changing workload conditions and ongoing evolving threats has enabled it to con-tinuously update the operational intelligence for the workloads it monitors. These findings indicate the importance for intelligent pre-dictive cloud security systems in protecting enterprise cloud infrastructures from increasingly complex and mature cyber threat actors. The proposed framework has laid a solid founda-tion for future growth in AI-driven cloud security management and dynamic predictive CSPM architectures. [2], [3].

[1]National Institute of Standards and Technology, “Security and Privacy Controls for Information Systems and Organizations,” NIST Special Publication 800-53 Revision 5, 2020. [2]Gartner Research, “Cloud Security Posture Management and Predictive Security Intelligence,” Gartner Technical Research Report, 2021. [3]S. Shin, J. Lee, and H. Kim, “AI-Based Cloud Security Monitoring and Predictive Threat Detection,” IEEE Access, vol. 8, pp. 184102–184115, 2020. [4]Cloud Security Alliance, “Cloud Security Guidance for Critical Areas of Focus in Cloud Computing,” CSA Research Report, 2021. [5]Google Cloud Security Team, “Google Cloud Security Foundations and Operational Best Practices,” Google Cloud Technical Documentation, 2022. [6]D. Fernandes, L. Soares, J. Gomes, M. Freire, and P. Inacio, “Security Issues in Cloud Environments: A Survey,” International Journal of Information Security, vol. 13, no. 2, pp. 113–170, 2019. [7]M. Alruwaili and K. Gulliver, “Predictive Security Analytics in Cloud Computing Using Machine Learning,” Journal of Cloud Computing, vol. 9, no. 4, pp. 1–15, 2020. [8]Y. Zhang and H. Liu, “Behavioral Anomaly Detection for Cloud Security Monitoring,” IEEE Transactions on Cloud Computing, vol. 9, no. 3, pp. 1142–1155, 2021. [9]IBM Cloud Security Research Team, “Cloud Threat Intelligence and Predictive Security Operations,” IBM Research Technical Report, 2021. [10]Microsoft Security Research, “AI-Driven Cloud Security and Oper-ational Threat Analytics,” Microsoft Azure Security Documentation, 2022.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close