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
@article{arxiv.2604.09695,
title = {Assessing Privacy Preservation and Utility in Online Vision-Language Models},
author = {Karmesh Siddharam Chaudhari and Youxiang Zhu and Amy Feng and Xiaohui Liang and Honggang Zhang},
journal= {arXiv preprint arXiv:2604.09695},
year = {2026}
}
Comments
Accepted for publication in IEEE ICC 2026. \c{opyright} IEEE. Personal use of this material is permitted. The final version will appear in IEEE Xplore