Towards Automating Data Access Permissions in AI Agents

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wu, Yuhao, Yang, Ke, Roesner, Franziska, Kohno, Tadayoshi, Zhang, Ning, Iqbal, Umar
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909917406822400
author Wu, Yuhao
Yang, Ke
Roesner, Franziska
Kohno, Tadayoshi
Zhang, Ning
Iqbal, Umar
author_facet Wu, Yuhao
Yang, Ke
Roesner, Franziska
Kohno, Tadayoshi
Zhang, Ning
Iqbal, Umar
contents As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission models are inadequate for the automated agentic execution paradigm. We therefore propose automated permission management for AI agents. Our key idea is to conduct a user study to identify the factors influencing users' permission decisions and to encode these factors into an ML-based permission management assistant capable of predicting users' future decisions. We find that participants' permission decisions are influenced by communication context but importantly individual preferences tend to remain consistent within contexts, and align with those of other participants. Leveraging these insights, we develop a permission prediction model achieving 85.1% accuracy overall and 94.4% for high-confidence predictions. We find that even without using permission history, our model achieves an accuracy of 66.9%, and a slight increase of training samples (i.e., 1-4) can substantially increase the accuracy by 10.8%.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17959
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Automating Data Access Permissions in AI Agents
Wu, Yuhao
Yang, Ke
Roesner, Franziska
Kohno, Tadayoshi
Zhang, Ning
Iqbal, Umar
Cryptography and Security
Artificial Intelligence
Human-Computer Interaction
Machine Learning
As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission models are inadequate for the automated agentic execution paradigm. We therefore propose automated permission management for AI agents. Our key idea is to conduct a user study to identify the factors influencing users' permission decisions and to encode these factors into an ML-based permission management assistant capable of predicting users' future decisions. We find that participants' permission decisions are influenced by communication context but importantly individual preferences tend to remain consistent within contexts, and align with those of other participants. Leveraging these insights, we develop a permission prediction model achieving 85.1% accuracy overall and 94.4% for high-confidence predictions. We find that even without using permission history, our model achieves an accuracy of 66.9%, and a slight increase of training samples (i.e., 1-4) can substantially increase the accuracy by 10.8%.
title Towards Automating Data Access Permissions in AI Agents
topic Cryptography and Security
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2511.17959