Assessing Privacy Preservation and Utility in Online Vision-Language Models

arXiv:2604.09695v1 Announce Type: cross Abstract: 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 explore