Towards Robust Red-Green Watermarking for Autoregressive Image Generators

• URL: http://arxiv.org/abs/2508.06656v1
• Date: Fri, 08 Aug 2025 19:14:22 GMT
• Title: Towards Robust Red-Green Watermarking for Autoregressive Image Generators
• Authors: Denis Lukovnikov, Andreas Müller, Erwin Quiring, Asja Fischer,
• Abstract summary: In this paper, we explore the use of in-generation watermarks in autoregressive (AR) image models.<n>AR models generate images by autoregressively predicting a sequence of visual tokens that are then decoded into pixels.<n>Inspired by red-green watermarks for large language models, we examine token-level watermarking schemes that bias the next-token prediction.<n>We propose two novel watermarking methods that rely on visual token clustering to assign similar tokens to the same set.
• Score: 17.784976310663104
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In-generation watermarking for detecting and attributing generated content has recently been explored for latent diffusion models (LDMs), demonstrating high robustness. However, the use of in-generation watermarks in autoregressive (AR) image models has not been explored yet. AR models generate images by autoregressively predicting a sequence of visual tokens that are then decoded into pixels using a vector-quantized decoder. Inspired by red-green watermarks for large language models, we examine token-level watermarking schemes that bias the next-token prediction based on prior tokens. We find that a direct transfer of these schemes works in principle, but the detectability of the watermarks decreases considerably under common image perturbations. As a remedy, we propose two novel watermarking methods that rely on visual token clustering to assign similar tokens to the same set. Firstly, we investigate a training-free approach that relies on a cluster lookup table, and secondly, we finetune VAE encoders to predict token clusters directly from perturbed images. Overall, our experiments show that cluster-level watermarks improve robustness against perturbations and regeneration attacks while preserving image quality. Cluster classification further boosts watermark detectability, outperforming a set of baselines. Moreover, our methods offer fast verification runtime, comparable to lightweight post-hoc watermarking methods.

Related papers

• 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)
• Diffusion-Based Image Editing for Breaking Robust Watermarks [4.273350357872755]
  Powerful diffusion-based image generation and editing techniques pose a new threat to robust watermarking schemes.<n>We show that a diffusion-driven image regeneration'' process can erase embedded watermarks while preserving image content.<n>We introduce a novel guided diffusion attack that explicitly targets the watermark signal during generation, significantly degrading watermark detectability.
  arXiv  Detail & Related papers  (2025-10-07T14:34:42Z)
• Watermarking Autoregressive Image Generation [2.6394824904757943]
  We present the first such approach by adapting language model watermarking techniques to this setting.<n>We identify a key challenge: the lack of reverse cycle-consistency.<n>We introduce (i) a custom tokenizer-detokenizer finetuning procedure that improves RCC, and (ii) a complementary watermark synchronization layer.
  arXiv  Detail & Related papers  (2025-06-19T14:25:51Z)
• Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models [50.73220224678009]
  Watermarking can be used to verify the origin of synthetic images generated by artificial intelligence models.<n>Recent studies demonstrate the capability to forge watermarks from a target image onto cover images via adversarial techniques.<n>In this paper, we uncover a greater risk of an optimization-free and universal watermark forgery.<n>Our approach significantly broadens the scope of attacks, presenting a greater challenge to the security of current watermarking techniques.
  arXiv  Detail & Related papers  (2025-06-06T12:08:02Z)
• Training-Free Watermarking for Autoregressive Image Generation [24.86897985016275]
  IndexMark is a training-free watermarking framework for autoregressive image generation models.<n>We show IndexMark achieves state-of-the-art performance in terms of image quality and verification accuracy.
  arXiv  Detail & Related papers  (2025-05-20T17:58:02Z)
• SEAL: Semantic Aware Image Watermarking [26.606008778795193]
  We propose a novel watermarking method that embeds semantic information about the generated image directly into the watermark.<n>The key pattern can be inferred from the semantic embedding of the image using locality-sensitive hashing.<n>Our results suggest that content-aware watermarks can mitigate risks arising from image-generative models.
  arXiv  Detail & Related papers  (2025-03-15T15:29:05Z)
• JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits [76.25962336540226]
  JIGMARK is a first-of-its-kind watermarking technique that enhances robustness through contrastive learning. Our evaluation reveals that JIGMARK significantly surpasses existing watermarking solutions in resilience to diffusion-model edits.
  arXiv  Detail & Related papers  (2024-06-06T03:31:41Z)
• RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees [33.61946642460661]
  This paper introduces a robust and agile watermark detection framework, dubbed as RAW. We employ a classifier that is jointly trained with the watermark to detect the presence of the watermark. We show that the framework provides provable guarantees regarding the false positive rate for misclassifying a watermarked image.
  arXiv  Detail & Related papers  (2024-01-23T22:00:49Z)
• WAVES: Benchmarking the Robustness of Image Watermarks [67.955140223443]
  WAVES (Watermark Analysis Via Enhanced Stress-testing) is a benchmark for assessing image watermark robustness. We integrate detection and identification tasks and establish a standardized evaluation protocol comprised of a diverse range of stress tests. We envision WAVES as a toolkit for the future development of robust watermarks.
  arXiv  Detail & Related papers  (2024-01-16T18:58:36Z)
• Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust [55.91987293510401]
  Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content. We introduce a novel technique called Tree-Ring Watermarking that robustly fingerprints diffusion model outputs. Our watermark is semantically hidden in the image space and is far more robust than watermarking alternatives that are currently deployed.
  arXiv  Detail & Related papers  (2023-05-31T17:00:31Z)
• 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)
• Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models [72.9364216776529]
  We propose a novel watermark removal attack from a different perspective. We design a simple yet powerful transformation algorithm by combining imperceptible pattern embedding and spatial-level transformations. Our attack can bypass state-of-the-art watermarking solutions with very high success rates.
  arXiv  Detail & Related papers  (2020-09-18T09:14:54Z)

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.