Mitigating Zero Day Vulnerabilities Using AI Based Threat Detection in Cloud Infrastructures

Sandra Rentería; Avery Desrosiers; Harper Middleton

Authors

Sandra Rentería Cloud Security Analyst, Mexico Author
Avery Desrosiers AI Threat Engineer, Canada Author
Harper Middleton Cyber Defense Architect, Australia Author

Keywords:

Zero-day vulnerabilities, Cloud security, AI-based detection, Threat mitigation, Machine learning, Cybersecurity, Anomaly detection

Abstract

Zero-day vulnerabilities represent one of the most critical threats to modern cloud infrastructures. These undiscovered and unpatched flaws are exploited by attackers before security vendors become aware of them. Traditional security measures often fail to detect such anomalies in time. The integration of artificial intelligence (AI) in threat detection systems offers a proactive mechanism capable of identifying previously unknown patterns and reducing response time. This paper explores the application of AI-driven threat detection in mitigating zero-day vulnerabilities within cloud environments. By leveraging machine learning and behavioral analysis, AI-based systems provide enhanced detection capabilities, increased accuracy, and reduced false positives. A comparative analysis with traditional systems illustrates the potential of AI in securing dynamic cloud infrastructures.

References

Tavabi, N., et al. (2018). A framework for detecting advanced cyber threats using machine learning. Journal of Cybersecurity, 4(1), 12–24.

Shaukat, K., et al. (2020). A review on AI-based intrusion detection systems for cloud environments. Future Generation Computer Systems, 107, 1025–1041.

Hodo, E., et al. (2016). Threat detection using artificial neural networks in cloud computing. Computers & Security, 61, 95–108.

Ullah, F., & Mahmoud, Q. (2019). A hybrid intrusion detection system using ensemble learning. Journal of Information Security and Applications, 47, 76–85.

Chung, H., & Lee, S. (2017). Security analysis for containerized cloud services. Journal of Network and Computer Applications, 88, 1–13.

Alshamrani, A., et al. (2019). Machine learning for automated cloud incident response. Computers & Security, 87, 101569.

Gao, L., et al. (2021). Artificial intelligence in cloud security: A comprehensive survey. ACM Computing Surveys, 54(6), 1–36.

Kumar, R., & Lata, M. (2017). Detection of zero-day threats using anomaly-based detection. International Journal of Computer Applications, 160(7), 25–30.

Subramanian, N., et al. (2018). Behavior-based zero-day attack detection in cloud networks. Computers & Electrical Engineering, 70, 123–132.

Ahmed, M., et al. (2020). Deep learning approaches for zero-day malware detection in cloud computing. Journal of Big Data, 7(1), 52.

Singh, S., & De, T. (2017). Securing public cloud APIs from zero-day attacks using AI models. Journal of Cloud Computing, 6(1), 10–18.

Yan, Q., et al. (2022). Cloud-native AI security detection framework using unsupervised learning. Information Sciences, 589, 75–91.

Zhou, Z., et al. (2021). Reinforcement learning for adaptive threat detection in containerized environments. IEEE Transactions on Cloud Computing, 9(4), 1147–1159.

Almseidin, M., et al. (2017). Evaluation of decision tree classifiers for zero-day attack detection. Procedia Computer Science, 109, 617–622.