Sketch-based Access Control: A Multimodal Interface for Translating User Preferences into Intent-Aligned Policies
TLDR
SBAC is an AI-assisted sketch-based system that simplifies creating and refining access control policies using multimodal LLMs.
Key contributions
- Introduces Sketch-based Access Control (SBAC), an AI-assisted system for authoring access control policies.
- Combines expressive sketching with multimodal LLMs for policy interpretation and validation.
- Proposes a human-AI collaborative workflow with Specify, Analyze, and Test stages.
- User studies show SBAC helps refine policies, surface gaps, and resolve ambiguities effectively.
Why it matters
Access control policy specification is complex and error-prone. This paper introduces a novel multimodal interface that simplifies this process. It enables users to iteratively refine policies, making security more accessible and robust.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.