AnchorMark: Robust Diffusion Watermarking via Latent-Space Rotation Synchrony
arXiv:2607.27551
The paper proposes AnchorMark, a training‑free inversion‑based watermarking method for diffusion models that uses a latent‑space rotation synchrony property to embed a central anchor, allowing accurate correction of image rotations during extraction and improving robustness against combined post‑processing attacks.
Abstract
Inversion-based watermarking embeds watermark payloads directly into the generative process, avoiding a separate post-hoc image-domain embedding stage while preserving the native visual fidelity of synthesized images. However, existing methods remain vulnerable to compound lossy post-processing, particularly when rotation is involved, as it disrupts the spatial correspondence required for latent-space decoding. To overcome this limitation, we introduce AnchorMark, a training-free, robust inversion-based watermarking. We uncover a latent-space property termed Rotation Synchrony: image-domain rotations and their counterparts in the recovered initial latent share the same angle. Building on this property, AnchorMark embeds a synchronization anchor in the central region of the initial latent, enabling accurate estimation and correction of the rotation angle during extraction. Experiments show that AnchorMark substantially improves bit accuracy under rotation and combined attacks, with limited impact on image quality.