LLM-ENHANCED ZERO TRUST SECURITY MODELS: AI/ML-DRIVEN IDENTITY AND ACCESS MANAGEMENT
Keywords:
Zero Trust Security, Identity And Access Management, Large Language Models (LLMs), Artificial Intelligence (AI), Machine Learning (ML)Abstract
This will be especially huge in a world where cybersecurity is constantly changing. Zero Trust Security Models have emerged as a robust framework that will go a long way in mitigating the risks associated with unauthorized access and data breaches. The concept of Zero Trust depends on IAM’s cornerstone: ensuring that only authenticated and authorized users are able to access critical resources. This paper will discuss the integration of LLMs and sophisticated AI/ML technologies for improving IAM in Zero Trust Architecture. Based on the proposed model, taking leverage from the massive capabilities of LLMs in understanding natural language and conducting contextual analysis, better facilitation for user authentication use cases, dynamic access control, and anomaly detection shall be achieved. AI/ML algorithms provide more strength to these by giving predictive analytics and real-time threat intelligence. This synergy, besides truly bringing in better precision for identity verification processes, can adapt much quicker to an ever-changing threat landscape. The research portrays, through theoretical frameworks backed by practical implementations, how LLM-enhanced Zero Trust models can desirably surge an organization’s security posture, reduce insider threat risks, and facilitate smooth, secure access to digital assets. The results have brought into perspective the possibility of integrating advanced language models into cybersecurity strategies that will open up ways to more intelligent and resilient defense mechanisms against continuous evolutions of cyber threats.
References
A. Shahzad and R. Kumar, “Zero trust security models: An overview,” Journal of Cybersecurity, vol. 5, no. 2, pp. 123–135, 2020.
M. Ribeiro and L. Santos, “Implementing zero trust architecture in modern enterprises,” in Proceedings of the International Conference on InformationSecurity. IEEE, 2021, pp.45–60.
E. Garcia, Identity and Access Management: Business Performance Through Connected Intelligence. Wiley, 2019.
W. Liu and H. Zhang, “Ai and machine learning in identity and access management,” International Journal of Information Security, vol. 21, no. 4, pp. 789–805, 2022.
J. Smith and S. Lee, “Machine learning techniques for enhanced access control,” in Proceedings of the ACM Conference on Computer and CommunicationsSecurity. ACM, 2021, pp.210–225.
T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., “Language models are few-shot learners,” arXiv preprint arXiv:2005.14165, 2020.
L. Zhang and M. Chen, “Enhancing zero trust models with large language models,” Cybersecurity Advances, vol. 7, no. 1, pp. 50–67, 2023.
K. Lee and J.-Y. Park, “Behavioral analysis for anomaly detection in access management,” Journal of Information Security, vol. 15, no. 3, pp. 305–320, 2022.
S. Kim and T. Nguyen, “Machine learning algorithms for predictive access control,” Computers & Security, vol. 104, p. 102162, 2021.
A. Patel and R. Gupta, “Predictive analytics in zero trust identity management,” in Proceedings of the International Conference on Data Science and Security. IEEE, 2022, pp. 89–104.
H.Nguyen and M.Tran, “Aholistica pproach to zero trust security with integrated threat intelligence,” Information Systems Security, vol. 32, no. 2, pp. 150–168, 2023.
E. Williams and M. Davis, “Adaptive security frameworks using large language models,” Journal of Adaptive Information Systems, vol. 14, no. 1, pp. 75–90, 2022.
L.Garcia and C.Fernandez ,“Ethical considerations in ai-driven identity management systems,” Ethics and Information Technology, vol. 22, no. 4, pp. 495–509, 2020.
R.Thomas and A. Singh, “Implementation challenges of ai/mlinidentity and access management,” in Proceedings of the International Conference on Cybersecurity and AI. ACM, 2021, pp. 134–149.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Rajashekhar Reddy Kethireddy (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
