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

Documentdetail

ID kaart

oai:arXiv.org:2409.10958

Onderwerp

Computer Science - Multimedia Computer Science - Cryptography an... Computer Science - Computer Vision... Electrical Engineering and Systems...

Auteur

Pan, Yongyang Liu, Xiaohong Luo, Siqi Xin, Yi Guo, Xiao Liu, Xiaoming Min, Xiongkuo Zhai, Guangtao

Categorie

Computer Science

Jaar

2024

vermelding datum

18-12-2024

Trefwoorden

science computer

Metriek

Beschrijving

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.

;Comment: 9 pages, 7 figures

Pan, Yongyang,Liu, Xiaohong,Luo, Siqi,Xin, Yi,Guo, Xiao,Liu, Xiaoming,Min, Xiongkuo,Zhai, Guangtao, 2024, Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending

Document

Openen

Bron

Artikelen aanbevolen door ES/IODE AI