Towards Automating Data Access Permissions in AI Agents

TL;DR

This paper introduces an ML-based system for automating data access permissions in AI agents, enhancing transparency and user control by predicting user decisions based on communication context and individual preferences.

Contribution

It presents a novel permission prediction model that leverages user study insights, achieving high accuracy and demonstrating the potential for automated permission management in AI agents.

Findings

Permission decisions are influenced by communication context.

User preferences are consistent within contexts.

Model achieves 85.1% overall accuracy.

Abstract

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%.