Uncertainty-Aware, Risk-Adaptive Access Control for Agentic Systems using an LLM-Judged TBAC Model

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fleming, Charles, Kundu, Ashish, Kompella, Ramana
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914090225500160
author Fleming, Charles
Kundu, Ashish
Kompella, Ramana
author_facet Fleming, Charles
Kundu, Ashish
Kompella, Ramana
contents The proliferation of autonomous AI agents within enterprise environments introduces a critical security challenge: managing access control for emergent, novel tasks for which no predefined policies exist. This paper introduces an advanced security framework that extends the Task-Based Access Control (TBAC) model by using a Large Language Model (LLM) as an autonomous, risk-aware judge. This model makes access control decisions not only based on an agent's intent but also by explicitly considering the inherent \textbf{risk associated with target resources} and the LLM's own \textbf{model uncertainty} in its decision-making process. When an agent proposes a novel task, the LLM judge synthesizes a just-in-time policy while also computing a composite risk score for the task and an uncertainty estimate for its own reasoning. High-risk or high-uncertainty requests trigger more stringent controls, such as requiring human approval. This dual consideration of external risk and internal confidence allows the model to enforce a more robust and adaptive version of the principle of least privilege, paving the way for safer and more trustworthy autonomous systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11414
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty-Aware, Risk-Adaptive Access Control for Agentic Systems using an LLM-Judged TBAC Model
Fleming, Charles
Kundu, Ashish
Kompella, Ramana
Cryptography and Security
The proliferation of autonomous AI agents within enterprise environments introduces a critical security challenge: managing access control for emergent, novel tasks for which no predefined policies exist. This paper introduces an advanced security framework that extends the Task-Based Access Control (TBAC) model by using a Large Language Model (LLM) as an autonomous, risk-aware judge. This model makes access control decisions not only based on an agent's intent but also by explicitly considering the inherent \textbf{risk associated with target resources} and the LLM's own \textbf{model uncertainty} in its decision-making process. When an agent proposes a novel task, the LLM judge synthesizes a just-in-time policy while also computing a composite risk score for the task and an uncertainty estimate for its own reasoning. High-risk or high-uncertainty requests trigger more stringent controls, such as requiring human approval. This dual consideration of external risk and internal confidence allows the model to enforce a more robust and adaptive version of the principle of least privilege, paving the way for safer and more trustworthy autonomous systems.
title Uncertainty-Aware, Risk-Adaptive Access Control for Agentic Systems using an LLM-Judged TBAC Model
topic Cryptography and Security
url https://arxiv.org/abs/2510.11414