Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{182382,
        author = {Atharva Thorat and Prashant Kulkarni and Vishnupant Potdar},
        title = {AI Based Zero Trust Security For Cloud Envoirnments},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {1447-1452},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182382},
        abstract = {With the growing shift toward cloud-native architectures, conventional perimeter-focused security approaches are no longer effective against advanced cyber threats. The dynamic, distributed, and virtualized nature of cloud systems demands a security paradigm that does not rely on trust by default. Zero Trust Security (ZTS) offers a new model, emphasizing continuous authentication, identity verification, and contextual policy enforcement. However, ZTS alone is insufficient without intelligent and adaptive detection capabilities. This research proposes a comprehensive AI-powered anomaly detection system integrated into the Zero Trust framework to safeguard cloud web traffic. The system utilizes AWS CloudWatch logs and employs a Random Forest classifier to detect and classify malicious activities such as Distributed Denial of Service (DDoS) attacks, SQL injection, and brute-force attempts. Through rigorous experimentation, the proposed model achieved a detection accuracy of 96.1%, with additional insights provided by SHAP-based explainability to ensure transparency and accountability. This framework not only enhances real-time decision-making within Zero Trust enforcement but also addresses the critical need for interpretability and cloud-native scalability.},
        keywords = {},
        month = {July},
        }