For blind and low-vision individuals, visual assistant applications such as BeMyAI and SeeingAI are used to answer questions about the world around them. These systems often advise users not to capture images containing personally identifiable information, but for many users, avoiding private content is difficult or impossible.
A recent study led by Stony Brook University, in partnership with the University of Texas at Austin and the University of Maryland, has introduced a new framework called FiG-Priv. This technology selectively hides only high-risk personal information in images sent to AI assistants. Sensitive details like account numbers or Social Security digits are concealed, while non-sensitive context—such as the type of form or a customer service 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 system works by detecting and segmenting private objects within an image—such as credit cards or financial statements—and producing a redacted version where risky content is obscured using black squares. The rest of the image remains clear so that visual assistants can still interpret useful context.
Jeffri Murrugarra-Llerena, PhD student and lead author on the project, said: “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 full story by Ankita Nagpal is available at the AI Innovation Institute website.
