cs.AI, cs.CL, cs.CR, cs.CV, cs.LG

To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model

arXiv:2605.14291v1 Announce Type: cross
Abstract: The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data, posing severe copyright and privacy risks to data…