FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space

YiYang Guo, Ruizhe Li, Mude Hui, Hanzhong Allan Guo, Chen Zhang, Chuangjian Cai, Le Wan, Shangfei Wang

Keywords: deep watermarking, latent frequency optimization

TL;DR: We propose a novel method for invisible watermark by optimizing the latent frequency space of images, named FreqMark, providing remarkable robustness and flexibility.

Abstract:

Invisible watermarking is essential for safeguarding digital content, enabling copyright protection and content authentication.
However, existing watermarking methods fall short in robustness against regeneration attacks.
In this paper, we propose a novel method called FreqMark that involves unconstrained optimization of the image latent frequency space obtained after VAE encoding. Specifically, FreqMark embeds the watermark by optimizing the latent frequency space of the images and then extracts the watermark through a pre-trained image encoder. This optimization allows a flexible trade-off between image quality with watermark robustness and effectively resists regeneration attacks.
Experimental results demonstrate that FreqMark offers significant advantages in image quality and robustness, permits flexible selection of the encoding bit number, and achieves a bit accuracy exceeding 90\% when encoding a 48-bit hidden message under various attack scenarios.

Primary Area: Privacy

Submission Number: 9375