AI-BASED DYNAMIC RISK SCORING FRAMEWORK FOR CLOUD SECURITY | IJCT Volume 13 – Issue 3 | IJCT-V13I3P29
International Journal of Computer Techniques
ISSN 2394-2231
Author
Abhay Tyagi, Amba Mishra
Abstract
Cloud computing has become a critical infrastructure for modern organizations due to its scalability, flexibility, and cost efficiency. However, the distributed and multi-tenant nature of cloud environments introduces significant security challenges, including data breaches, insider threats, misconfigurations, insecure interfaces, and advanced cyberattacks. Traditional cloud security mechanisms rely on static policies and reactive defenses, which are insufficient for addressing rapidly evolving threats. This paper proposes an Artificial Intelligence (AI)-based Dynamic Risk Index (DRI) framework for real-time cloud security management. The proposed approach integrates continuous monitoring, machine learning–based anomaly detection, impact assessment, and vulnerability analysis to compute a quantitative risk score for each activity within the cloud environment. Based on this score, adaptive security controls such as multi-factor authentication, access restriction, and resource isolation are automatically enforced according to predefined risk thresholds. Unlike conventional detection-only solutions, the framework provides an end-to-end mechanism that combines threat identification, risk evaluation, and automated response. Experimental evaluation using a simulated environment demonstrates that the proposed model achieves high detection accuracy while maintaining a low false-positive rate. The results indicate that the Dynamic Risk Index framework can significantly enhance cloud resilience by enabling proactive, context-aware security management.
Keywords
Cloud computing security, Dynamic risk assessment, Artificial intelligence, Anomaly detection, Adaptive security, Zero trust architecture, Intrusion detection, Risk management.
Conclusion
This paper presented an Artificial Intelligence–based Dynamic Risk Index (DRI) framework for enhancing security in cloud computing environments. The proposed approach addresses the limitations of traditional static security mechanisms by providing real-time risk evaluation and adaptive protection. By integrating continuous monitoring, machine learning–based anomaly detection, impact assessment, and vulnerability analysis, the framework computes a quantitative risk score that reflects both the likelihood and severity of potential threats. Based on this score, appropriate security measures are automatica ly enforced, enabling proactive defense against cyberattacks.
Experimental evaluation using a simulated cloud environment demonstrated that the framework achieves high detection accuracy while maintaining a low false-positive rate. The results indicate that the DRI model can effectively prioritize security incidents and reduce response time compared with conventional detection-only systems. The ability to apply graduated security controls according to risk levels helps balance protection and usability, which is essential for maintaining service availability in cloud infrastructures.
The proposed framework contributes to the advancement of intelligent cloud security by integrating threat detection, risk assessment, and automated response into a unified system. Unlike existing approaches that focus primarily on alert generation, the DRI framework supports context-aware decision making and reduces reliance on manual intervention.
Future work will focus on implementing the framework in real-world cloud platforms and evaluating its performance using large-scale operational datasets. Additional research will explore the integration of advanced machine learning models, privacy-preserving techniques, and cross-cloud threat intelligence sharing. These enhancements aim to further improve scalability, accuracy, and resilience against emerging cyber threats.
Overall, the Dynamic Risk Index framework represents a promising direction for next-generation cloud security solutions, enabling organizations to protect critical assets in increasingly complex and dynamic computing environments.
References
[1][1] A Survey on Cloud Security: Concepts, Types, Limitations, and Challenges.
[2][2] R. Soni and N. Uikey, “Cloud Computing Security and Challenges: An In-Depth Analysis,” International Journal on Science and Technology, vol. 16, no. 2, 2025.
[3][3] K. Hashizume et al., “An analysis of security issues for cloud computing,” Journal of Internet Services and Applications, 2013.
[4][4] S. Subashini and V. Kavitha, “A survey on security issues in service delivery models of cloud computing,” Journal of Network and Computer Applications, 2011.
[5][5] M. Armbrust et al., “A view of cloud computing,” Communications of the ACM, 2010.
[6][6] P. Mell and T. Grance, “The NIST definition of cloud computing,” NIST Special Publication 800-145, 2011.
[7][7] Cloud Security Alliance, “Security guidance for critical areas of focus in cloud computing,” CSA Report, 2017.
[8][8] J. Rittinghouse and J. Ransome, Cloud Computing: Implementation, Management, and Security, CRC Press, 2017.
[9][9] S. Pearson, “Privacy when designing cloud computing services,” IEEE Cloud Computing, 2016.
[10][10] A. Singh and K. Chatterjee, “Cloud security issues and challenges: A survey,” Journal of Network and Computer Applications, 2017.
[11][11] J. Srinivas et al., “Cloud computing basics,” International Journal of Advanced Research in Computer and Communication Engineering, 2012.
[12][12] Z. Xiao and Y. Xiao, “Security and privacy in cloud computing,” IEEE Communications Surveys & Tutorials, 2013.
[13][13] S. Zhang et al., “Cloud computing research trends,” IEEE Conference on Future Networks, 2010.
[14][14] D. Chen and H. Zhao, “Data security issues in cloud computing,” IEEE Conference on Computer Science, 2012.
[15] N. Gonzalez et al., “Security concerns and solutions for cloud computing,” Journal of Cloud Computing, 201
How to Cite This Paper
Abhay Tyagi, Amba Mishra (2026). AI-BASED DYNAMIC RISK SCORING FRAMEWORK FOR CLOUD SECURITY. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
