Understanding Semantic Perturbations on In-Processing Generative Image Watermarks

• URL: http://arxiv.org/abs/2603.27513v1
• Date: Sun, 29 Mar 2026 04:34:44 GMT
• Title: Understanding Semantic Perturbations on In-Processing Generative Image Watermarks
• Abstract summary: We introduce a framework for systematically stress-testing in-processing generative watermarks under semantic drift.<n>We find that robustness varies significantly with the degree of semantic entanglement.<n>Our results suggest that watermark designs and benchmarking must explicitly account for robustness against semantic manipulation.
• Score: 7.3040623979718475
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authentication. In-processing watermarking, embedding a signature into the generative model's synthesis procedure, has been advocated as a solution and is often reported to be robust to standard post-processing (such as geometric transforms and filtering). Yet robustness to semantic manipulations that alter high-level scene content while maintaining reasonable visual quality is not well studied or understood. We introduce a simple, multi-stage framework for systematically stress-testing in-processing generative watermarks under semantic drift. The framework utilizes off-the-shelf models for object detection, mask generation, and semantically guided inpainting or regeneration to produce controlled, meaning-altering edits with minimal perceptual degradation. Based on extensive experiments on representative schemes, we find that robustness varies significantly with the degree of semantic entanglement: methods by which watermarks remain detectable under a broad suite of conventional perturbations can fail under semantic edits, with watermark detectability in many cases dropping to near zero while image quality remains high. Overall, our results reveal a critical gap in current watermarking evaluations and suggest that watermark designs and benchmarking must explicitly account for robustness against semantic manipulation.

Related papers

• Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio [58.612001688217056]
  Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization inconsistencies.<n>We propose an elegant solution for powerful and robust watermarking of synthetic audio.
  arXiv  Detail & Related papers  (2026-05-25T15:43:20Z)
• SAiW: Source-Attributable Invisible Watermarking for Proactive Deepfake Defense [7.442956390854273]
  Deepfakes generated by modern generative models pose a serious threat to information integrity, digital identity, and public trust.<n>We introduce SAiW, a Source-Attributed Invisible watermarking Framework for proactive deepfake defense and media provenance verification.
  arXiv  Detail & Related papers  (2026-03-24T13:26:52Z)
• Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarking [0.3644540605358075]
  diffusion-based image editing injects noise and reconstructs images through a powerful generative prior.<n>We show that non-adversarial diffusion editing can unintentionally degrade or remove robust watermarks.<n>Results indicate that even routine semantic edits can significantly reduce watermark recoverability.
  arXiv  Detail & Related papers  (2026-03-13T12:46:27Z)
• When Denoising Becomes Unsigning: Theoretical and Empirical Analysis of Watermark Fragility Under Diffusion-Based Image Editing [0.0]
  In parallel, diffusion-based image editing has rapidly matured into a default transformation layer for modern content pipelines.<n>This paper studies a subtle but increasingly consequential interaction between these trends.<n>We show that watermark payloads behave as low-energy, high-frequency signals that are systematically attenuated by the forward diffusion step.<n>We discuss ethical implications, responsible disclosure norms, and concrete design guidelines for watermarking schemes that remain meaningful in the era of generative transformations.
  arXiv  Detail & Related papers  (2026-03-05T00:26:34Z)
• WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models [79.32764976020435]
  Digital watermarking is essential for securing generated images from diffusion models.<n>Previous watermark evaluation methods lack a unified framework for both residual and semantic watermarks.<n>We proposeLM, the first unified and interpretable evaluation framework for diffusion model image watermarking via vision-language models.
  arXiv  Detail & Related papers  (2026-01-29T12:14:32Z)
• An Ensemble Framework for Unbiased Language Model Watermarking [60.99969104552168]
  We propose ENS, a novel ensemble framework that enhances the detectability and robustness of unbiased watermarks.<n>ENS sequentially composes multiple independent watermark instances, each governed by a distinct key, to amplify the watermark signal.<n> Empirical evaluations show that ENS substantially reduces the number of tokens needed for reliable detection and increases resistance to smoothing and paraphrasing attacks.
  arXiv  Detail & Related papers  (2025-09-28T19:37:44Z)
• StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models [55.05404953041403]
  We propose a novel framework that seamlessly integrates a binary watermark into the diffusion generation process.<n>We show that StableGuard consistently outperforms state-of-the-art methods in image fidelity, watermark verification, and tampering localization.
  arXiv  Detail & Related papers  (2025-09-22T16:35:19Z)
• A Watermark for Auto-Regressive Image Generation Models [50.599325258178254]
  We propose C-reweight, a distortion-free watermarking method explicitly designed for image generation models.<n>C-reweight mitigates retokenization mismatch while preserving image fidelity.
  arXiv  Detail & Related papers  (2025-06-13T00:15:54Z)
• Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal [57.84348166457113]
  We introduce a novel feature adapting framework that leverages the representation capacity of a pre-trained image inpainting model.<n>Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model.<n>For relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process.
  arXiv  Detail & Related papers  (2025-04-07T02:37:14Z)
• Robust Identity Perceptual Watermark Against Deepfake Face Swapping [9.402982368385569]
  Deepfake face swapping has caused critical privacy issues with the rapid development of deep generative models.<n>We propose a robust identity perceptual watermarking framework that concurrently performs detection and source tracing against Deepfake face swapping.
  arXiv  Detail & Related papers  (2023-11-02T16:04:32Z)

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.