Generative Model Watermarking Based on Human Visual System

Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing. However, the existing watermarking methods designed for generative models do not take into acc...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Zhang, Li, Liu, Yong, Liu, Shaoteng, Yang, Tianshu, Wang, Yexin, Zhang, Xinpeng, Wu, Hanzhou
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 30.09.2022
Subjects
Artificial neural networks
Channels
Color
Embedding
Image processing
Watermarking
Online AccessGet full text

Cover

More Information
Summary:Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing. However, the existing watermarking methods designed for generative models do not take into account the effects of different channels of sample images on watermarking. As a result, the watermarking performance is still limited. To tackle this problem, in this paper, we first analyze the effects of embedding watermark information on different channels. Then, based on the characteristics of human visual system (HVS), we introduce two HVS-based generative model watermarking methods, which are realized in RGB color space and YUV color space respectively. In RGB color space, the watermark is embedded into the R and B channels based on the fact that HVS is more sensitive to G channel. In YUV color space, the watermark is embedded into the DCT domain of U and V channels based on the fact that HVS is more sensitive to brightness changes. Experimental results demonstrate the effectiveness of the proposed work, which improves the fidelity of the model to be protected and has good universality compared with previous methods.
ISSN:2331-8422