eISSN: 3087-4289 editor@aimjournals.com
All Journals
Submit your article

International Journal of Modern Computer Science and IT Innovations

Open Access Peer Review International
Open Access

AI-Driven Governance and Risk Management of Non-Human Identities in Cloud IAM Environments

DOI https://doi.org/10.55640/ijmcsit-v03i09-01
PDF
Faisal Al-Harbi 1 , Reem Al-Qahtani 1 ,
4 Department of Information Technology, Arabian Institute of Computing and Technology, Saudi Arabia
4 Department of Information Technology, Arabian Institute of Computing and Technology, Saudi Arabia

Abstract

The rapid adoption of cloud-native applications, Internet of Things (IoT) platforms, edge computing, machine learning services, autonomous workloads, and application-to-application communication has substantially increased the number and complexity of non-human identities (NHIs) operating within modern cloud environments. Unlike conventional human identities, NHIs—including service accounts, workload identities, application credentials, machine identities, API identities, and automated agents—can execute privileged operations continuously and at machine speed. Consequently, conventional identity governance models centered primarily on human authentication and periodic access reviews are insufficient for dynamically changing machine-to-machine interactions. This paper examines an AI-driven governance and risk-management framework for NHIs in Cloud Identity and Access Management (IAM) environments. The study adopts a conceptual research-and-review methodology based exclusively on the supplied literature and develops a governance model incorporating identity discovery, contextual risk assessment, least-privilege enforcement, behavioral monitoring, lifecycle management, and adaptive policy decisions. The literature indicates that distributed edge-cloud architectures create heterogeneous workloads, decentralized execution points, and dynamic communication patterns that increase the importance of automated governance. Existing work on edge-cloud computing, IoT platforms, accelerated machine-learning workloads, and distributed detection systems demonstrates the operational complexity associated with such environments. The analysis extends these observations to NHI governance and argues that AI can improve continuous identity visibility and risk prioritization, but should operate within explainable, policy-constrained governance boundaries. The resulting framework emphasizes continuous rather than periodic governance and establishes risk-aware controls for the creation, use, privilege escalation, rotation, and retirement of NHIs.

Keywords

Non-Human Identities, Cloud IAM, Artificial Intelligence, Identity Governance

References

A. Briley and F. Afghah, “Hardware acceleration for real-time wildfire detection onboard drone networks,” in Proc. IEEE INFOCOM 2024—IEEE Conf. on Computer Communications Workshops (INFOCOM WKSHPS), Vancouver, Canada, 2024, pp. 1–6.
G. Chenglin et al., “Real-time fire detection and alarm system using edge computing and cloud IoT platform,” Int. J. Wireless Mobile Comput., vol. 22, nos. 3/4, pp. 310–318, 2022.
Dong et al., “PG-YOLO: A novel lightweight object detection method for edge devices in industrial Internet of Things,” IEEE Access, vol. 10, pp. 123736–123745, 2022.
M. A. Firdaus, “Prototype smart integrated fire detection based on deep learning YOLOv8 and IoT (Internet of Things) to improve early fire detection,” Int. J. Appl. Math., Sci. Technol. Natl. Defense, vol. 2, no. 2, 2024.
Google Research, “Get started with the USB accelerator,” Edge TPU Documentation.
S. Hall, “Fire loss in the United States during 2023,” NFPA Research, 2024. Accessed: Jan. 2, 2025.
Mamadaliev et al., “ESFD-YOLOv8n: Early smoke and fire detection method based on an improved YOLOv8n model,” Fire, vol. 7, no. 9, p. 303, 2024.
W. F. Magalhães et al., “Investigating mobile edge-cloud trade-offs of object detection with YOLO,” in Proc. Symp. Knowledge Discovery, Mining and Learning (KDMiLe), Porto Alegre, Brazil, 2019, pp. 49–56.
S. Saponara et al., “Enabling YOLOv2 models to monitor fire and smoke detection remotely in smart infrastructures,” in Lecture Notes in Electrical Engineering, vol. 738. Cham, Switzerland: Springer, 2021.
M. A. Saleem, “An edge computing infrastructure and deep learning methods for wildfire monitoring and anomalies detection,” Ph.D. dissertation, Ministry of Higher Education, 2022.
Shamta and B. E. Demir, “Development of a deep learning-based surveillance system for forest fire detection and monitoring using UAV,” PLoS ONE, vol. 19, no. 3, Art. no. e0299058.
State and Agency, “2018 National year-to-date report on fires and acres burned,” National Interagency Fire Center, 2024. Accessed: Jan. 2, 2025.
F. M. Talaat and H. ZainEldin, “An improved fire detection approach based on YOLO-v8 for smart cities,” Neural Comput. Appl., vol. 35, pp. 20939–20954, 2023.
P. Weichao et al., “EFA-YOLO: An efficient feature attention model for fire and flame detection,” Computer Vision and Pattern Recognition.
S. Liang and X. Zhang, “An object detection system for automatic driving: MEC-YOLO based on cloud-edge-end,” in Proc. 6th Int. Conf. Natural Language Processing (ICNLP), Xi'an, China, 2024, pp. 536–541.
G. Jocher et al., “YOLOv10—Ultralytics YOLO documents,” Ultralytics, 2024.
S. Ganapathy, “Automated governance and protection of non-human identities in cloud IAM,” Frontiers in Emerging Computer Science and Information Technology, vol. 2, no. 2, pp. 8–20, 2025. [Online]. Available: https://irjernet.com/index.php/fecsit/article/view/cloud-iam-non-human-identities