Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
As visual assistant systems powered by visual language models (VLMs) become more prevalent, concerns over user privacy have grown, particularly for blind and low vision users who may unknowingly capture personal private information in their images. Existing privacy protection methods rely on coarse-grained segmentation, which uniformly masks entire private objects, often at the cost of usability. In this work, we propose FiGPriv, a fine-grained privacy protection framework that selectively masks only high-risk private information while preserving low-risk information. Our approach integrates fine-grained segmentation with a data-driven risk scoring mechanism. We evaluate our framework using the BIV-Priv-Seg dataset and show that FiG-Priv preserves +26% of image content, enhancing the ability of VLMs to provide useful responses by 11% and identify the image content by 45%, while ensuring privacy protection. Project Page: https://artcs1.github.io/VLMPrivacy/
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Analysis of Shuffling Beyond Pure Local Differential Privacy
Shuffling is a powerful way to amplify privacy of a local randomizer in private distributed data analysis. Most existing analyses of how shuffling amplifies privacy are based on the pure local differential privacy (DP) p…
Accelerating Evolution Through Gene Masking and Distributed Search
In building practical applications of evolutionary computation (EC), two optimizations are essential. First, the parameters of the search method need to be tuned to the domain in order to balance exploration and exploita…
BLANKET: Anonymizing Faces in Infant Video Recordings
Ensuring the ethical use of video data involving human subjects, particularly infants, requires robust anonymization methods. We propose BLANKET (Baby-face Landmark-preserving ANonymization with Keypoint dEtection consis…
Keypoint DetectionPose EstimationFace SwappingMarkov Blanket Ranking using Kernel-based Conditional Dependence Measures
Developing feature selection algorithms that move beyond a pure correlational to a more causal analysis of observational data is an important problem in the sciences. Several algorithms attempt to do so by discovering th…
feature selectionStable Blanket with Hidden Variables and Cycles
Stabilized regression aims to identify a set of predictors whose conditional relationship with a response variable remains invariant across different environments. Existing graphical characterizations of the stable blank…