Sketch-based Access Control: A Multimodal Interface for Translating User Preferences into Intent-Aligned Policies
2026-05-11 • Human-Computer Interaction
Human-Computer InteractionCryptography and Security
AI summaryⓘ
The authors created a new system called Sketch-based Access Control (SBAC) that helps people easily make rules about who can access certain resources. It uses drawing (sketching) combined with AI that understands language to help users write and check these rules step-by-step. In tests with real users, the system helped people improve their initial rule ideas by finding unclear parts and testing if the rules worked as intended. This made it easier to create clear and complete access policies.
Access ControlUsable SecuritySketching InterfaceMultimodal Large Language ModelsPolicy SpecificationHuman-AI CollaborationUsability StudyIterative Refinement
Authors
Kyzyl Monteiro, Sauvik Das
Abstract
Developing simple and expressive access controls -- interfaces to specify policies that define who should have access to resources and under what circumstances -- is a longstanding challenge in usable security. We present Sketch-based Access Control (SBAC), a sketch-based, AI-assisted access control authoring system that combines the expressive power of sketching with the interpretive capabilities of multimodal large language models (MLLMs) to support the interpretation and validation of policy specifications as they are iteratively refined. Through a formative study with 14 participants, we identified three design requirements and developed a human-AI collaborative workflow composed of three stages -- Specify, Analyze, and Test -- enabled by the system's ability to maintain and interpret evolving access control specifications. In a user evaluation with 14 participants grounded in their real-world access control scenarios, we found the system and the workflow helped participants progressively refine initially underspecified preferences into more complete and precise policies -- surfacing gaps they had not anticipated, resolving ambiguities through dialogue, and validating policy behavior through concrete scenarios.