Where is the Watermark? Interpretable Watermark Detection at the Block Level
This addresses the need for transparent watermarking to enhance trust and interpretability in digital media protection, though it is incremental as it builds on prior post-hoc methods.
The paper tackles the problem of black-box watermarking in images by introducing a post-hoc method that provides interpretable detection maps at the block level, achieving strong robustness against transformations like cropping up to half the image while maintaining high imperceptibility.
Recent advances in generative AI have enabled the creation of highly realistic digital content, raising concerns around authenticity, ownership, and misuse. While watermarking has become an increasingly important mechanism to trace and protect digital media, most existing image watermarking schemes operate as black boxes, producing global detection scores without offering any insight into how or where the watermark is present. This lack of transparency impacts user trust and makes it difficult to interpret the impact of tampering. In this paper, we present a post-hoc image watermarking method that combines localised embedding with region-level interpretability. Our approach embeds watermark signals in the discrete wavelet transform domain using a statistical block-wise strategy. This allows us to generate detection maps that reveal which regions of an image are likely watermarked or altered. We show that our method achieves strong robustness against common image transformations while remaining sensitive to semantic manipulations. At the same time, the watermark remains highly imperceptible. Compared to prior post-hoc methods, our approach offers more interpretable detection while retaining competitive robustness. For example, our watermarks are robust to cropping up to half the image.