# Assessing Privacy Preservation and Utility in Online Vision-Language Models

arXiv: https://arxiv.org/abs/2604.09695 · HTML: https://mlsanity.com/paper/2604.09695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences](https://mlsanity.com/paper/2406.11069/) (2024)
- [PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles](https://mlsanity.com/paper/2410.17127/) (2024)
- [Private Attribute Inference from Images with Vision-Language Models](https://mlsanity.com/paper/2404.10618/) (2024)
- [PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy](https://mlsanity.com/paper/2001.00561/) (2020)
- [DP-Image: Differential Privacy for Image Data in Feature Space](https://mlsanity.com/paper/2103.07073/) (2021)
- [Generative Visual Commonsense Answering and Explaining with Generative Scene Graph Constructing](https://mlsanity.com/paper/2501.09041/) (2025)

## Abstract (arXiv)

The increasing use of Online Vision Language Models (OVLMs) for processing images has introduced significant privacy risks, as individuals frequently upload images for various utilities, unaware of the potential for privacy violations. Images contain relationships that relate to Personally Identifiable Information (PII), where even seemingly harmless details can indirectly reveal sensitive information through surrounding clues. This paper explores the critical issue of PII disclosure in images uploaded to OVLMs and its implications for user privacy. We investigate how the extraction of contextual relationships from images can lead to direct (explicit) or indirect (implicit) exposure of PII, significantly compromising personal privacy. Furthermore, we propose methods to protect privacy while preserving the intended utility of the images in Vision Language Model (VLM)-based applications. Our evaluation demonstrates the efficacy of these techniques, highlighting the delicate balance between maintaining utility and protecting privacy in online image processing environments. Index Terms-Personally Identifiable Information (PII), Privacy, Utility, privacy concerns, sensitive information