Vision Language Model Helps Private Information De-Identification in Vision Data 事件

Vision Language Model Helps Private Information De-Identification in Vision Data arXiv:2606.09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability. While various methods exist to enhance privacy in text-based applications, privacy risks associated with visual inputs remain largely overlooked such as Protected Health Information (PHI) in medical images. To tackle this problem, two key tasks: accurately localizing sens