Towards Automating Data Access Permissions in AI Agents
This addresses transparency and control issues for users of AI agents, though it is incremental as it builds on existing permission models with a novel automated approach.
The paper tackles the problem of automating data access permissions for AI agents by developing a machine learning model that predicts users' permission decisions based on factors identified from a user study, achieving 85.1% overall accuracy and 94.4% for high-confidence predictions.
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%.