paper-with-me

홈 › Papers

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users

2025-08-12 · Jeffri Murrugarra-LLerena, Haoran Niu, K. Suzanne Barber, Hal Daumé, Yang Trista Cao, Paola Cascante-Bonilla arxiv

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/

📄 PDF Abstract BibTeX arXiv:2508.09245

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Analysis of Shuffling Beyond Pure Local Differential Privacy

2026-01-27 · Shun Takagi, Seng Pei Liew arxiv

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

2023-02-13 · Hormoz Shahrzad, Risto Miikkulainen

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

2025-12-17 · Ditmar Hadera, Jan Cech, Miroslav Purkrabek, Matej Hoffmann arxiv

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 Swapping

Markov Blanket Ranking using Kernel-based Conditional Dependence Measures

2014-02-01 · Eric V. Strobl, Shyam Visweswaran

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 selection

Stable Blanket with Hidden Variables and Cycles

2026-05-03 · Hanqing Xiang arxiv

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…