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

arXiv: https://arxiv.org/abs/2508.09245 · HTML: https://mlsanity.com/paper/2508.09245/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 18 of 18)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://mlsanity.com/paper/2203.10638/) (2022)
- [Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps](https://mlsanity.com/paper/2209.12836/) (2022)
- [BOP: Benchmark for 6D Object Pose Estimation](https://mlsanity.com/paper/1808.08319/) (2018)
- [CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers](https://mlsanity.com/paper/2207.02202/) (2022)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [Privacy Preserving Machine Learning: Threats and Solutions](https://mlsanity.com/paper/1804.11238/) (2018)
- [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024)
- [PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network](https://mlsanity.com/paper/2104.05458/) (2021)
- [Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking](https://mlsanity.com/paper/2406.09598/) (2024)
- [CORE: Cooperative Reconstruction for Multi-Agent Perception](https://mlsanity.com/paper/2307.11514/) (2023)
- [QUEST: Query Stream for Practical Cooperative Perception](https://mlsanity.com/paper/2308.01804/) (2023)
- [CoopDETR: A Unified Cooperative Perception Framework for 3D Detection via Object Query](https://mlsanity.com/paper/2502.19313/) (2025)
- [BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments](https://mlsanity.com/paper/2407.18243/) (2024)
- [Privacy Risk Predictions Based on Fundamental Understanding of Personal Data and an Evolving Threat Landscape](https://mlsanity.com/paper/2508.04542/) (2025)

## Built on by (most cited first, 2 of 2)

- [Unsafe2Safe: Controllable Image Anonymization for Downstream Utility](https://mlsanity.com/paper/2603.28605/) (2026)
- [See No Evil: Semantic Context-Aware Privacy Risk Detection for AR](https://mlsanity.com/paper/2604.22805/) (2026)

## Abstract (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/