Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Pan, Yongyang, Liu, Xiaohong, Luo, Siqi, Xin, Yi, Guo, Xiao, Liu, Xiaoming, Min, Xiongkuo, Zhai, Guangtao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929631954731008
author Pan, Yongyang
Liu, Xiaohong
Luo, Siqi
Xin, Yi
Guo, Xiao
Liu, Xiaoming
Min, Xiongkuo
Zhai, Guangtao
author_facet Pan, Yongyang
Liu, Xiaohong
Luo, Siqi
Xin, Yi
Guo, Xiao
Liu, Xiaoming
Min, Xiongkuo
Zhai, Guangtao
contents Rapid advancements in multimodal large language models have enabled the creation of hyper-realistic images from textual descriptions. However, these advancements also raise significant concerns about unauthorized use, which hinders their broader distribution. Traditional watermarking methods often require complex integration or degrade image quality. To address these challenges, we introduce a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB). TEAWIB incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models. This approach ensures that each user can directly apply a pre-configured set of parameters to the model without altering the original model parameters or compromising image quality. Additionally, noise and augmentation operations are embedded at the pixel level to further secure and stabilize watermarked images. Extensive experiments validate the effectiveness of TEAWIB, showcasing the state-of-the-art performance in perceptual quality and attribution accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2409_10958
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending
Pan, Yongyang
Liu, Xiaohong
Luo, Siqi
Xin, Yi
Guo, Xiao
Liu, Xiaoming
Min, Xiongkuo
Zhai, Guangtao
Multimedia
Cryptography and Security
Computer Vision and Pattern Recognition
Image and Video Processing
Rapid advancements in multimodal large language models have enabled the creation of hyper-realistic images from textual descriptions. However, these advancements also raise significant concerns about unauthorized use, which hinders their broader distribution. Traditional watermarking methods often require complex integration or degrade image quality. To address these challenges, we introduce a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB). TEAWIB incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models. This approach ensures that each user can directly apply a pre-configured set of parameters to the model without altering the original model parameters or compromising image quality. Additionally, noise and augmentation operations are embedded at the pixel level to further secure and stabilize watermarked images. Extensive experiments validate the effectiveness of TEAWIB, showcasing the state-of-the-art performance in perceptual quality and attribution accuracy.
title Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending
topic Multimedia
Cryptography and Security
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2409.10958