For individuals who are blind or have low vision, visual assistant applications such as BeMyAI and SeeingAI offer quick answers to questions about their surroundings. These tools can interpret text on forms or provide details about bills. However, using these services often means sharing images that may contain sensitive personal information, raising privacy concerns for users.
Researchers from Stony Brook University, the University of Texas at Austin, and the University of Maryland have developed a new system called FiG-Priv to address these concerns. The framework is designed to hide only high-risk personal information in images submitted to AI assistants. Details like account numbers and Social Security digits are obscured, while less sensitive context—such as the type of form or a customer service phone number—remains visible.
Paola Cascante-Bonilla, assistant professor in the Department of Computer Science at Stony Brook University and co-author of the study, described the limitations of previous methods: “Traditional masking techniques to protect sensitive information often blur or black-out entire objects. For blind and low-vision users, this is impractical. Masking too much destroys the utility of the content, while masking too little leaks sensitive data. FiG-Priv aims to allow BLV users to interact with AI systems without exposing personal information. It focuses only on the sensitive content.”
The FiG-Priv system works by detecting private items within an image—such as credit cards or financial statements—and then obscuring those specific areas with black squares. The rest of the image remains clear so that AI visual assistants can still interpret it.
Jeffri Murrugarra-Llerena, PhD student and lead author of the study, highlighted how this approach helps users: “Blind and low-vision users should be able to support both their independence and their privacy. In previous approaches, they were forced to choose one over the other. With our approach, users can ask questions more confidently, without worrying about what these systems might reveal.”
The research aims to improve privacy protection for BLV individuals while preserving access to important visual information through AI-based assistance.
