Cloud Sentinel-AI: An Explainable Behavioral-Provenance and Self-Healing Security Framework for Autonomous AI Agents in Multi-Cloud Environments
DOI:
https://doi.org/10.46610/JFIHC.2026.v03i03.004Keywords:
Autonomous AI Agents, Behavioral Provenance, CloudSentinel-AI, Explainable AI, Risk Assessment, Self-Healing Security, Threat DetectionAbstract
The rapid adoption of autonomous artificial intelligence (AI) agents in cloud environments has introduced new security challenges due to their ability to dynamically select tools, access heterogeneous resources, interpret external information, and modify execution plans at runtime. Conventional authentication and static authorization mechanisms are often insufficient to capture the evolving security context of such agent-driven activities. This study proposes CloudSentinel-AI, an explainable, behavior-aware, and self-healing security framework for protecting autonomous AI agents operating across multi-cloud environments. The proposed framework continuously constructs a behavioral provenance model that links agent identity, task context, data sources, tool invocations, API operations, cloud resources, and resulting actions. A hybrid detection mechanism combines behavioral analysis, contextual risk assessment, and provenance-deviation analysis to identify potentially malicious or unauthorized agent behavior. An explainable decision layer associates detected risks with supporting evidence and determines proportional security responses, including additional verification, capability restriction, credential revocation, and agent isolation. The proposed prototype architecture integrates Python, FastAPI, PostgreSQL-compatible storage, graph-oriented provenance representation, Docker-based deployment, a web-based monitoring dashboard, and a Flutter mobile client. To support reproducible evaluation, the CloudSentinel-AgentSec Dataset (CASD) is proposed as a synthetic benchmark containing normal and adversarial autonomous-agent sessions. The evaluation methodology considers precision, recall, F1-score, false-positive rate, detection latency, containment latency, and system resource overhead. No performance claims are made until the prototype is evaluated using the defined benchmark. The proposed work therefore provides a reproducible technical architecture and systematic evaluation methodology for improving the security, explainability, and resilience of autonomous AI agents in multi-cloud environments.
References
Y. Tang, Y. Liu, J. Lan, Z. Yan, and E. Gelenbe, “Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey,” Information Fusion, vol. 127, Mar. 2026.
H. Zhang et al., “Agent security bench (ASB): Formalizing and benchmarking attacks and defenses in LLM-based agents,” International Conference on Learning Representations, 2025.
R. Chandramouli and Z. Butcher, A Zero Trust Architecture Model for Access Control in Cloud-Native Applications in Multi-Cloud Environments, NIST Special Publication 800-207A. Gaithersburg, MD, USA: National Institute of Standards and Technology, Sep. 2023.
H. Booth, W. Fisher, R. Galluzzo, and J. Roberts, Accelerating the Adoption of Software and Artificial Intelligence Agent Identity and Authorization. National Institute of Standards and Technology, Feb. 5, 2026.
S. Rose, O. Borchert, S. Mitchell, and S. Connelly, Zero Trust Architecture, NIST Special Publication 800-207. Gaithersburg, MD, USA: National Institute of Standards and Technology, Aug. 2020.
Samed AL and S. Sagiroglu, “Explainable artificial intelligence models in intrusion detection systems,” Engineering Applications of Artificial Intelligence, vol. 144, Mar. 2025.
A. Sharma, S. Rani, and M. Shabaz, “A comprehensive review of explainable AI in cybersecurity: Decoding the black box,” ICT Express, vol. 11, no. 6, Dec. 2025.
D. Manivannan, “A comprehensive analysis of explainable AI-driven machine learning techniques for network intrusion detection systems,” High-Confidence Computing, vol. 6, no. 4, Dec. 2026.
B. Bhoi, G. Jethava and S. Jethava, “A comprehensive review of anomaly detection techniques for insider threat identification,” 2026 International Conference on AI-Driven Smart Systems and Ubiquitous Computing (ICAUC), Pathum Thani, Thailand, 2026, pp. 1050–1056.
T. Gasmi, R. Guesmi, J. Bennaceur, and I. Belhadj, “Bridging AI and software security: A comparative vulnerability assessment of LLM agent deployment paradigms,” Information Sciences, vol. 740, Jun. 2026.
V. H. G. Moia, I. J. Sanz, G. A. F. Rebello, R. D. de Meneses, B. Hitaj, and U. Lindqvist, “LLM in the middle: A systematic review of threats and mitigations to real-world LLM-based systems,” Computer Science Review, vol. 61, Aug. 2026.
J. Riggs, M. Hamin, N. Perry, B. Edelman, and P. Cihon, Summary Analysis of Responses to the Request for Information Regarding Security Considerations for AI Agents, NIST Trustworthy and Responsible AI, Rep. 800-5. Gaithersburg, MD, USA: National Institute of Standards and Technology, May 2026.
