FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
This addresses copyright protection and content authentication for digital content, offering a robust solution against regeneration attacks, though it appears incremental as it builds on existing watermarking methods.
The paper tackles the problem of invisible image watermarking being vulnerable to regeneration attacks by proposing FreqMark, a method that optimizes the latent frequency space of images, resulting in over 90% bit accuracy for a 48-bit hidden message under various attacks.
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.