AnchorMark: Robust Diffusion Watermarking via Latent-Space Rotation Synchrony

• URL: http://arxiv.org/abs/2607.27551v1
• Date: Thu, 30 Jul 2026 00:52:48 GMT
• Title: AnchorMark: Robust Diffusion Watermarking via Latent-Space Rotation Synchrony
• Abstract summary: Inversion-based watermarking embeds payloads directly into the generative process.<n>We introduce AnchorMark, a training-free, robust inversion-based watermarking.
• Score: 4.208755585274347
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images [5.8272908076992715]
  Most in-generation diffusion watermarks embed patterns independent of the image that carries them, and attackers transplant the marks onto images the generator did not produce.<n>We present IRIS, a training-free watermarking scheme that embeds an Intrinsic Ring Identifier from Semantics.
  arXiv  Detail & Related papers  (2026-08-04T12:16:06Z)
• SPFM-Net: Semantic-Prior-Guided Frequency-Constrained Mamba for Invisible Watermark Attack [13.95278003579795]
  SPFM-Net is a semantic-prior-guided and frequency-constrained Mamba framework for invisible watermark attack.<n> SPFM-Net first employs high-ratio masking to disrupt the spatial coherence of invisible watermark signals.<n>A lightweight Mamba-based Global State-space Feature Modeling unit is introduced to separate watermark-related features from natural image content.
  arXiv  Detail & Related papers  (2026-07-30T07:50:49Z)
• FARI: Robust One-Step Inversion for Watermarking in Diffusion Models [89.29541056113442]
  Inversion-based watermarking is a promising approach to authenticate diffusion-generated images.<n>Existing approaches over-optimize internal truncation error.<n>textbfFARI is a one-step inversion framework paired with lightweight adversarial LoRA fine-tuning of the denoiser for watermark extraction.
  arXiv  Detail & Related papers  (2026-07-29T10:13:55Z)
• BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models [0.0]
  BiSLW is a trainable bi-spectral latent watermarking framework that embeds aligned identity signals across complementary spectral bands.<n>Low-frequency components encode global semantics, while high-frequency components capture fine texture.<n>BiSLW achieves a strong balance between fidelity and robustness, improving PSNR by over 3 dB compared to prior latent diffusion watermarking methods.
  arXiv  Detail & Related papers  (2026-07-02T17:48:54Z)
• OSI: One-step Inversion Excels in Extracting Diffusion Watermarks [56.210696479553945]
  We propose One-step Inversion (OSI), a significantly faster and more accurate method for extracting Gaussian Shading style watermarks.<n>OSI reformulates watermark extraction as a learnable sign classification problem, which eliminates the need for precise regression of the initial noise.<n>Our OSI substantially outperforms the multi-step diffusion inversion method: it is 20x faster, achieves higher extraction accuracy, and doubles the watermark payload capacity.
  arXiv  Detail & Related papers  (2026-02-10T07:43:16Z)
• MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation [37.899449138826725]
  MarkCleaner is a watermark removal framework that avoids semantic drift caused by regeneration-based watermark removal.<n>We show that MarkCleaner achieves superior performance in both watermark removal effectiveness and visual fidelity.
  arXiv  Detail & Related papers  (2026-02-02T01:03:21Z)
• RAVEN: Erasing Invisible Watermarks via Novel View Synthesis [35.417500510522835]
  In this work, we expose a fundamental vulnerability in invisible watermarks by reformulating watermark removal as a view synthesis problem.<n>Our key insight is that generating a perceptually consistent alternative view of the same semantic content, naturally removes the embedded watermark while preserving visual fidelity.<n>We introduce a zero-shot diffusion-based framework that applies controlled geometric transformations in latent space, augmented with view-guided correspondence attention to maintain structural consistency during reconstruction.
  arXiv  Detail & Related papers  (2026-01-13T18:59:58Z)
• OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization [66.69924980864053]
  We propose OptMark, an optimization-based approach that embeds a robust multi-bit watermark into the intermediate latents of the diffusion denoising process.<n> OptMark strategically inserts a structural watermark early to resist generative attacks and a detail watermark late to withstand image transformations.<n> Experimental results demonstrate that OptMark achieves invisible multi-bit watermarking while ensuring robust resilience against valuemetric transformations, geometric transformations, editing, and regeneration attacks.
  arXiv  Detail & Related papers  (2025-08-29T15:50:59Z)
• SSyncOA: Self-synchronizing Object-aligned Watermarking to Resist Cropping-paste Attacks [14.886729577388822]
  cropping-paste attack breaks the synchronization of the image watermark. Key to resisting the cropping-paste attack lies in robust features of the object to protect. We propose a self-synchronizing object-aligned watermarking method, called SSyncOA.
  arXiv  Detail & Related papers  (2024-05-06T13:29:34Z)
• Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal [63.576748565274706]
  This study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks.
  arXiv  Detail & Related papers  (2023-12-22T02:19:23Z)
• WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning [68.00975867932331]
  Existing watermark removal methods mainly rely on UNet with task-specific decoder branches. We introduce an implicit joint learning paradigm to holistically integrate information from both branches. The results demonstrate our approach's remarkable superiority, surpassing existing state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2023-08-20T07:56:34Z)
• Watermarking Images in Self-Supervised Latent Spaces [75.99287942537138]
  We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time.
  arXiv  Detail & Related papers  (2021-12-17T15:52:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.