Generative Model Watermarking Based on Human Visual System

TL;DR

This paper introduces two human visual system-based watermarking methods for generative models, embedding watermarks in color channels considering HVS sensitivity, thereby enhancing fidelity and universality of model protection.

Contribution

It proposes novel HVS-based watermarking techniques in RGB and YUV spaces that improve robustness and fidelity for protecting generative models.

Findings

Improved watermarking fidelity compared to previous methods

Effective embedding in R, B, U, V channels based on HVS sensitivity

Enhanced universality and robustness of watermarking

Abstract

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.