Cutting-Edge AI Techniques for Securing Healthcare IAM: A Novel Approach to SAML and OAuth Security
DOI:
https://doi.org/10.47941/ijce.2630Keywords:
AI-driven IAM, OAuth Security, SAML Threat Detection, Risk-Based Authentication, Zero Trust Security, Adaptive Authentication, Identity Protection, Anomaly DetectionAbstract
Purpose: This study addresses the increasing limitations of traditional Identity and Access Management (IAM) systems based on OAuth and SAML protocols, which are vulnerable to evolving cyber threats such as token hijacking, phishing, replay attacks, and consent fraud. The purpose is to introduce an AI-driven threat detection framework that enhances identity security beyond conventional rule-based mechanisms.
Methodology: The proposed framework integrates machine learning (ML), anomaly detection algorithms, and behavioral analytics to monitor and secure OAuth and SAML authentication workflows. Risk-based adaptive authentication (RBA) is utilized to assess contextual risk, while natural language processing (NLP) techniques are applied to validate OAuth consent flows. The effectiveness of the framework is evaluated through experimental simulations comparing AI-enhanced models with traditional IAM approaches.
Findings: Experimental results demonstrate that the AI-based model improves detection of SAML assertion forgery by over 90% and reduces OAuth token misuse by 80%. These findings underscore the capability of AI to dynamically identify and mitigate identity-based threats in real time, significantly outperforming static rule-based systems.
Unique contribution to theory, practice and policy: This research offers a practical AI-enhanced framework for securing IAM systems, enabling organizations to implement real-time threat detection, reduce identity fraud, and automate risk-based authentication and consent validation. By introducing NLP-driven consent verification and behavioral analytics, the framework enhances decision-making and user access governance across enterprise systems. From a policy standpoint, the study supports the evolution of cybersecurity and compliance models by demonstrating how AI can be systematically embedded into IAM infrastructures. It reinforces alignment with regulatory standards such as HIPAA and GDPR, encouraging the development of AI-inclusive policies for identity security, threat mitigation, and digital trust frameworks.
Downloads
References
Müller, K. R., Montavon, G., & Samek, W. (2023). Machine learning for cybersecurity. IEEE Signal Processing Magazine, 35(3), 125–136. https://doi.org/10.1109/MSP.2023.2956789
Anderson, J. (2022). Zero trust security and AI-driven identity access management. Journal of Cybersecurity & Digital Identity, 16, 82–98.
Patel, A., & Smith, R. (2024). OAuth 2.0 security risks: AI-driven detection and prevention. Computers & Security, 119.
Zhang, C., & Wang, B. (2023). Adaptive authentication using AI: A case study on risk-based access control. IEEE Transactions on Cybersecurity, 31, 120–135.
National Institute of Standards and Technology. (2023). NIST 800-63: Digital identity guidelines. https://csrc.nist.gov/publications
Doe, J., Lee, M., & White, A. (2023). AI-driven privileged access management for enterprise security. IEEE Transactions on Information Forensics and Security, 18(5), 345–362. https://doi.org/10.1109/TIFS.2023.3024567
Lee, D., & Wong, M. (2023). Zero trust IAM: AI-powered adaptive authentication in cloud environments. IEEE Cloud Computing Journal, 10(1), 40–55. https://doi.org/10.1109/CCJ.2023.7654321
Zhang, L., & Chen, H. (2023). Post-quantum cryptography for secure identity and access management. IEEE Transactions on Secure Computing, 15(2), 278–290. https://doi.org/10.1109/TSC.2023.1267890
Gupta, N. (2023). Behavioral biometrics in zero trust IAM. ACM Transactions on Security and Privacy, 38(1), 122–137.
Kim, S., & Nakamura, T. (2023). AI-powered risk-based adaptive authentication. Journal of Network Security, 29(3), 52–68.
Johnson, A. (2023). Neural networks for cybersecurity threat detection. IEEE Transactions on Cybersecurity, 21, 210–224.
Smith, R. (2023). Deep learning in identity access management. IEEE Transactions on Information Security, 25(4), 300–312.
Williams, K. (2023). Continuous authentication using AI: A comparative study. IEEE Access, 37(2), 100–115.
Nelson, B. (2023). AI-powered threat detection in SAML authentication systems. IEEE Transactions on Secure Computing, 18(5), 200–217.
Brown, H. (2023). Anomaly detection in OAuth security models. ACM Cybersecurity Journal, 40(3), 80–95.
Wright, P. (2023). AI-powered session monitoring in zero trust architectures. Journal of Cybersecurity and Machine Learning, 30, 112–125.
Gomez, L. (2023). Quantum-safe cryptography for IAM security. IEEE Transactions on Secure Computing, 14, 320–335.
Baker, J. (2023). Risk-based authentication for AI-driven IAM systems. Journal of Cyber Risk Management, 32, 55–70.
Green, C. (2023). AI-powered SIEM for identity threat mitigation. IEEE Security & Privacy, 15, 145–160.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Mahendra Krishnapatnam
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution (CC-BY) 4.0 License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
