An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Dongdong, Li, Yue, Tondi, Benedetta, Lin, Kaiqing, Li, Bin, Barni, Mauro
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908653848625152
author Lin, Dongdong
Li, Yue
Tondi, Benedetta
Lin, Kaiqing
Li, Bin
Barni, Mauro
author_facet Lin, Dongdong
Li, Yue
Tondi, Benedetta
Lin, Kaiqing
Li, Bin
Barni, Mauro
contents The rapid proliferation of Deep Neural Networks (DNNs) is driving a surge in model watermarking technologies, as the trained models themselves constitute valuable intellectual property. Existing watermarking approaches primarily focus on modifying model parameters or altering sampling behaviors. However, with the emergence of increasingly large models, improving the efficiency of watermark embedding becomes essential to manage increasing computational demands. Prioritizing efficiency not only optimizes resource utilization, making the watermarking process more applicable for large models, but also mitigates potential degradation of model performance. In this paper, we propose an efficient watermarking method for Latent Diffusion Models (LDMs) based on Low-Rank Adaptation (LoRA). The core idea is to introduce trainable low-rank parameters into the frozen LDM to embed watermark, thereby preserving the integrity of the original model weights. Furthermore, a dynamic loss weight scheduler is designed to adaptively balance the objectives of generative quality and watermark fidelity, enabling the model to achieve effective watermark embedding with minimal impact on quality of the generated images. Experimental results show that the proposed method ensures fast and accurate watermark embedding and a high quality of the generated images, at the same time maintaining a level of robustness aligned - in some cases superior - with state-of-the-art approaches. Moreover, the method generalizes well across different datasets and base LDMs. Codes are available at: https://github.com/MrDongdongLin/EW-LoRA.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20202
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting
Lin, Dongdong
Li, Yue
Tondi, Benedetta
Lin, Kaiqing
Li, Bin
Barni, Mauro
Computer Vision and Pattern Recognition
The rapid proliferation of Deep Neural Networks (DNNs) is driving a surge in model watermarking technologies, as the trained models themselves constitute valuable intellectual property. Existing watermarking approaches primarily focus on modifying model parameters or altering sampling behaviors. However, with the emergence of increasingly large models, improving the efficiency of watermark embedding becomes essential to manage increasing computational demands. Prioritizing efficiency not only optimizes resource utilization, making the watermarking process more applicable for large models, but also mitigates potential degradation of model performance. In this paper, we propose an efficient watermarking method for Latent Diffusion Models (LDMs) based on Low-Rank Adaptation (LoRA). The core idea is to introduce trainable low-rank parameters into the frozen LDM to embed watermark, thereby preserving the integrity of the original model weights. Furthermore, a dynamic loss weight scheduler is designed to adaptively balance the objectives of generative quality and watermark fidelity, enabling the model to achieve effective watermark embedding with minimal impact on quality of the generated images. Experimental results show that the proposed method ensures fast and accurate watermark embedding and a high quality of the generated images, at the same time maintaining a level of robustness aligned - in some cases superior - with state-of-the-art approaches. Moreover, the method generalizes well across different datasets and base LDMs. Codes are available at: https://github.com/MrDongdongLin/EW-LoRA.
title An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.20202