Are Semantic Watermarks for Diffusion Models Resilient to Layout Control?
Track: tiny / short paper (3-5 pages)
Keywords: semantic watermarking, controlnets, gaussian shading, treering
TL;DR: We check if semantic watermarks (Tree-Ring, Gaussian Shading) are still recoverable when they are used together with ControlNets and image regeneration using an inpainting model.
Abstract: Semantic watermarking methods embed information into generated images by modifying the initial latent noise, subtly modifying the output images. However, the widespread use of layout control techniques, such as ControlNets, raises questions about the applicability of semantic watermarking with layout control. After all, if semantic watermarks are really realized as meaningful changes in images (such as its layout), external layout specifications (e.g. through edge maps), could destroy the watermark information during denoising. This work empirically evaluates two semantic watermarking approaches---Tree-Ring Watermarking and Gaussian Shading---under various ControlNet-guided generation settings. Our results show that while ControlNets can slightly degrade watermark strength, both watermarking approaches remain largely detectable, demonstrating the potential viability of semantic watermarks even under strong layout constraints.
Presenter: ~Andreas_Müller2
Format: Maybe: the presenting author will attend in person, contingent on other factors that still need to be determined (e.g., visa, funding).
Funding: Yes, the presenting author of this submission falls under ICLR’s funding aims, and funding would significantly impact their ability to attend the workshop in person.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Submission Number: 29
Loading