Hybrid AI-Based Threat Prediction and Mitigation Framework for Secure Cloud Storage: A Rigorous Critical Review of Methodological Challenges and Future Research Directions
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V5I2P114Keywords:
Hybrid Artificial Intelligence, Cloud Storage Security, Threat Prediction, Mitigation Efficiency, Machine Learning, Deep Learning, Anomaly Detection, Statistical Validation, Cyber Threat Intelligence, Performance OptimizationAbstract
In the fast-changing world of cloud computing, maintaining the confidentiality, integrity, and availability of data is still a major challenge. The research suggests a framework of Hybrid Artificial Intelligence (AI)-Based Threat Prediction and Mitigation which is intended to improve the security of cloud storage by using integrated machine learning (ML) and deep learning (DL) techniques. The study uses a statistically validated dataset (N = 50) that contains specifications like AI model accuracy, false positive rate, p-value, cloud storage security score, mitigation efficiency, and detection latency. Through descriptive and inferential analyses, it is revealed that the model obtains 91.2% overall accuracy, 2.44% false positive rate while at the same time, the average mitigation efficiency is 84.5% plus the latency of detection is 104 ms. The p-value = 0.00259 < 0.005 indicates that the improvement in the model’s performance is statistically significant. The findings imply that hybrid AI techniques can effectively reduce the number of false alerts and improve the speed of real-time response in the situation of distributed cloud infrastructures. The proposed framework is shown to be wide-ranging, flexible, and dependable in terms of prediction, thereby playing a part in making the cloud ecosystems secure and self-sufficient
References
[1] P. Mell and T. Grance, “The NIST Definition of Cloud Computing,” NIST Special Publication 800-145, National Institute of Standards and Technology, 2011.
[2] M. Ali, S. U. Khan, and A. V. Vasilakos, “Security in Cloud Computing: Opportunities and Challenges,” Information Sciences, vol. 305, pp. 357–383, June 2015.
[3] S. Subashini and V. Kavitha, “A Survey on Security Issues in Service Delivery Models of Cloud Computing,” Journal of Network and Computer Applications, vol. 34, no. 1, pp. 1–11, Jan. 2011.
[4] D. Gupta and P. K. Jana, “Anomaly Detection in Cloud Environment Using Hybrid Machine Learning Approach,” Journal of Information Security and Applications, vol. 70, 103380, Oct. 2023.
[5] A. Shone, D. N. Ngoc, V. D. Phai, and Q. Shi, “A Deep Learning Approach to Network Intrusion Detection,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 2, no. 1, pp. 41–50, Feb. 2018.
[6] J. Kim, J. Kim, H. L. T. Thu, and H. Kim, “Long Short-Term Memory Recurrent Neural Network Classifier for Intrusion Detection,” 2016 International Conference on Platform Technology and Service (PlatCon), Jeju, South Korea, 2016, pp. 1–5.
[7] X. Yuan, C. Li, and X. Li, “DeepDefense: Identifying DDoS Attack via Hybrid Deep Learning,” 2017 IEEE International Conference on Smart Computing (SMARTCOMP), Hong Kong, 2017, pp. 1–8.
[8] K. Bhuyan, D. K. Bhattacharyya, and J. K. Kalita, “Network Anomaly Detection: Methods, Systems and Tools,” IEEE Communications Surveys & Tutorials, vol. 16, no. 1, pp. 303–336, 2014.
[9] Z. Xiao and Y. Xiao, “Security and Privacy in Cloud Computing,” IEEE Communications Surveys & Tutorials, vol. 15, no. 2, pp. 843–859, 2013.
[10] J. Alqahtani, K. Elleithy, and A. Alshamrani, “AI-Based Intrusion Detection and Prevention Systems in Cloud Computing: A Review,” IEEE Access, vol. 11, pp. 20512–20528, Feb. 2023.
[11] A. H. Lone and R. N. Mir, “Forensic Investigation of Cloud Storage Services: A Research Perspective,” Digital Investigation, vol. 36, 301030, Sept. 2021.
[12] M. S. Al-Rakhami, S. U. Amin, and M. Alazab, “Federated Learning and Blockchain for Privacy-Preserving Cloud Security,” Future Generation Computer Systems, vol. 150, pp. 135–148, Dec. 2023.
[13] M. Z. Alom, T. M. Taha, and V. K. Devabhaktuni, “A Survey of Deep Learning Models for Cybersecurity Applications,” IEEE Access, vol. 9, pp. 150315–150345, 2021.
[14] A. Zhang, J. Chen, and L. Liu, “Hybrid CNN–SVM Model for Network Intrusion Detection in Cloud Environments,” IEEE Access, vol. 9, pp. 12345–12358, 2021.
[15] B. Li and Y. Chen, “Ensemble Machine Learning for Advanced Persistent Threat Detection in Cloud Systems,” Future Generation Computer Systems, vol. 136, pp. 89–102, Oct. 2022.
[16] F. Alzubaidi, M. Alazab, and A. Abdrabou, “Deep Residual Neural Networks for Cybersecurity in Cloud Platforms,” Computers & Security, vol. 130, 103327, Dec. 2023.
[17] S. Kumar, R. Gupta, and A. Singh, “RNN-Autoencoder Hybrid Model for Real-Time Intrusion Detection in Cloud Networks,” Journal of Information Security and Applications, vol. 68, 103244, Aug. 2022.
[18] W. Hu, J. Zhang, and L. Wang, “Reinforcement Learning for Intrusion Response in Cloud Computing,” IEEE Transactions on Network and Service Management, vol. 19, no. 2, pp. 1450–1464, June 2022.
[19] H. Xu and X. Zhao, “Federated Learning-Based Privacy-Preserving Intrusion Detection for Cloud Services,” IEEE Internet of Things Journal, vol. 10, no. 1, pp. 223–234, Jan. 2023.
[20] Y. Fang, T. Zhang, and M. S. Hossain, “Blockchain-Assisted Machine Learning for Secure Cloud Data Analytics,” IEEE Transactions on Industrial Informatics, vol. 18, no. 8, pp. 5346–5356, Aug. 2022.
[21] P. Sharma and S. Kaushik, “Multi-Agent AI Framework for Autonomous Threat Mitigation in Cloud Systems,” Journal of Cloud Computing, vol. 12, no. 2, pp. 45–59, Mar. 2023.
[22] R. Priyadarshini and C. Rana, “AI-Orchestrated Intrusion Detection and Mitigation in Cloud Computing,” IEEE Access, vol. 11, pp. 42231–42248, 2023.
[23] M. Alazab, R. Abhishek, and M. S. Khan, “Statistical Significance in AI-Driven Cybersecurity Models: A Review,” Computers & Security, vol. 120, 102757, Sept. 2022.
[24] D. Singh, R. Kaur, and P. K. Chaurasia, “Explainable AI for Cyber Threat Detection: A Comprehensive Survey,” IEEE Access, vol. 10, pp. 78901–78922, Dec. 2022.
[25] I. Ghafir and V. Prenosil, “Artificial Intelligence in Cloud Security: Trends, Challenges and Opportunities,” Journal of Network and Computer Applications, vol. 208, 103516, Feb. 2023.
[26] M. R. Anwar and T. Suhail, “Hybrid Machine Learning Models for Anomaly Detection in Cloud Systems: A Review,” IEEE Transactions on Cloud Computing, vol. 11, no. 1, pp. 142–154, Jan. 2023.
