FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models

arXiv:2310.02401v2 Announce Type: replace-cross
Abstract: Text-to-image generative models, especially those based on latent diffusion models (LDMs), have demonstrated outstanding ability in generating high-quality and high-resolution images from textual prompts. With this advancement, various fine-tuning methods have been developed to personalize text-to-image models for specific applications such as artistic style adaptation and human face transfer. However, such advancements have raised copyright concerns, especially when the data are used for personalization without authorization. For example, a malicious user can employ fine-tuning techniques …

adaptation advancement applications arxiv cs.cr cs.cv diffusion models fine-tuning generative generative models high image images prompts quality resolution shield text unauthorized