EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Action-Centric Zero Trust Maturity Model for Agentic AI Environments

Jung-Hyun Mok iD, Hyun Jo, Sokjoon Lee iD

Sensors · 17.08.2026 · 26 (16) · 5205

DOI: 10.3390/s26165205 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.08.2026. Verfasst von Jung-Hyun Mok und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Security, Gachon University, Seongnam-si 13120, Republic of Korea. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation, Gachon University, Korea government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language model–based agentic AI systems can independently interpret user goals, develop plans, and interact with external tools. These capabilities introduce security concerns that extend beyond traditional access control. However, existing Zero Trust Maturity Models, such as the CISA ZTMM, mainly focus on how resources are accessed and provide limited guidance on how to evaluate actions taken after access has been granted. This paper proposes AI-ZTMM, which extends CISA’s five-pillar structure to action-level trust evaluation. The model defines forty-one security Functions based on ten threat categories and thirty-one security requirements and introduces Action Space and seven Action Risk Factors for organizational self-assessment. Its scope includes software agents and the software action layer of agents in IoT, robotic, and OT/ICS environments. The model was refined through reviews by eleven domain experts and evaluated using thirty-eight MITRE ATLAS case studies. The CISA ZTMM lacked directly relevant controls for 59.7% of the analyzed attack stages, whereas AI-ZTMM addressed 75.4% of this gap, achieving a combined direct coverage of 84.4%. These results show that AI-ZTMM complements the CISA ZTMM by providing action-level security controls.

Schlagwörter

Stichwörter der Autor:innen

AI agent securityZero Trustmaturity model

Autor:innen und Institutionen

  • Department of Information Security, Gachon University, Seongnam-si 13120, Republic of Korea.
  • Information Security Office, Korea Western Power, 285, Jungang-ro, Taean-eup, Taean-gun 32140, Republic of Korea.
  • Department of Smart Security, Gachon University, Seongnam-si 13120, Republic of Korea.

ORCID-Profile: Jung-Hyun Mok, Sokjoon Lee

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation
  • Gachon University
  • Korea government
  • Development of Core Technology for Intelligent O-RAN Security Platform

Zitieren

APA

Mok, J. H., Jo, H., & Lee, S. (2026). An Action-Centric Zero Trust Maturity Model for Agentic AI Environments. Sensors, 26(16), 5205. https://doi.org/10.3390/s26165205

Vancouver

Mok JH, Jo H, Lee S. An Action-Centric Zero Trust Maturity Model for Agentic AI Environments. Sensors. 2026;26(16):5205. doi:10.3390/s26165205

BibTeX
@article{Mok2026,
  author = {Mok, Jung-Hyun and Jo, Hyun and Lee, Sokjoon},
  title = {An Action-Centric Zero Trust Maturity Model for Agentic AI Environments},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {16},
  pages = {5205},
  doi = {10.3390/s26165205}
}
Kostenlos starten →