Attribute-based Undetectable Watermarking for Generative AI Models

• URL: http://arxiv.org/abs/2608.03174v1
• Date: Tue, 04 Aug 2026 06:05:58 GMT
• Title: Attribute-based Undetectable Watermarking for Generative AI Models
• Abstract summary: We introduce the first emphattribute-based watermarking for generative AI models.<n>We formalize its security properties, including consistency, adaptive robustness to bounded corruptions, undetectability, and soundness.<n>Our construction integrates constrained pseudorandom functions, pseudorandom error-correcting codes, and recovery procedures with generative AI models.
• Score: 5.283970991624705
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-generated outputs. Existing cryptographic watermarking methods provide strong undetectability guarantees: without a detection key, watermarked outputs are computationally indistinguishable from unwatermarked ones. However, these approaches do not address the crucial deployment challenge of how to safely delegate detection capabilities. With an unrestricted detection key, a malicious detector may use the detection key beyond its intended scope, enabling watermark sanitization, scope abuse, and user profiling. To mitigate this safety concern, we introduce, to the best of our knowledge, the first \emph{attribute-based watermarking} for generative AI models, providing fine-grained, policy-controlled watermark detection. In our approach, each generated output is associated with attributes, and each detection key is \emph{constrained by a policy} on potential attributes. A detection key can only be used to detect watermarked outputs whose attributes satisfy the corresponding policy, while watermarked outputs that fall outside the policy remain computationally indistinguishable from unwatermarked ones. We construct such an attribute-based watermarking scheme and formalize its security properties, including consistency, adaptive robustness to bounded corruptions, undetectability, and soundness, along with a security proof under standard cryptographic assumptions. Our construction integrates constrained pseudorandom functions, pseudorandom error-correcting codes, and randomness recovery procedures with generative AI models. Finally, we implement a prototype and an empirical evaluation, demonstrating that attribute-based watermarking is both effective and practical.

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)
• VOW: Verifiable and Oblivious Watermark Detection for Large Language Models [4.920744236528847]
  We propose a new protocol that achieves both privacy-preserving and cryptographically verifiable watermark detection.<n>VOW is practical for short texts and provides a crucial reassessment of watermark robustness against modern paraphrasing attacks.
  arXiv  Detail & Related papers  (2026-04-30T10:02:18Z)
• On the Robustness of Watermarking for Autoregressive Image Generation [21.402408065930796]
  Autoregressive (AR) image generators demand reliable detection and attribution of their outputs to prevent model collapse.<n>Watermarking techniques, specifically designed for AR models, embed a subtle signal at generation time, enabling downstream verification.<n>We study these schemes and demonstrate their vulnerability to both watermark removal and forgery attacks.
  arXiv  Detail & Related papers  (2026-04-13T16:56:48Z)
• Character-Level Perturbations Disrupt LLM Watermarks [64.60090923837701]
  We formalize the system model for Large Language Model (LLM) watermarking.<n>We characterize two realistic threat models constrained on limited access to the watermark detector.<n>We demonstrate character-level perturbations are significantly more effective for watermark removal under the most restrictive threat model.<n> Experiments confirm the superiority of character-level perturbations and the effectiveness of the Genetic Algorithm (GA) in removing watermarks under realistic constraints.
  arXiv  Detail & Related papers  (2025-09-11T02:50:07Z)
• When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting [37.85082375268253]
  We study the robustness of model-specific watermarking, where watermark embedding is integrated with text-to-image generation.<n>We introduce three attack strategies: edge prediction-based, box blurring, and fine-tuning-based attacks in a no-box setting.<n>Our best-performing attack achieves a reduction in watermark detection accuracy to approximately 47.92%.
  arXiv  Detail & Related papers  (2025-07-04T15:22:20Z)
• Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models [66.54457339638004]
  Copyright protection and inappropriate content generation pose challenges for the practical implementation of diffusion models.<n>We propose a diffusion model watermarking method tailored for real-world deployment.<n>Gaussian Shading++ not only maintains performance losslessness but also outperforms existing methods in terms of robustness.
  arXiv  Detail & Related papers  (2025-04-21T11:18:16Z)
• Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation [21.41643665626451]
  We propose an attack framework that extracts leakage of watermark patterns using a pre-trained vision model.<n>Unlike prior works requiring massive data or detector access, our method achieves both forgery and detection evasion with a single watermarked image.<n>Our work exposes the robustness-stealthiness paradox: current "robust" watermarks sacrifice security for distortion resistance, providing insights for future watermark design.
  arXiv  Detail & Related papers  (2025-02-10T12:55:08Z)
• Robustness of Watermarking on Text-to-Image Diffusion Models [9.277492743469235]
  We investigate the robustness of generative watermarking, which is created from the integration of watermarking embedding and text-to-image generation processing. We found that generative watermarking methods are robust to direct evasion attacks, like discriminator-based attacks, or manipulation based on the edge information in edge prediction-based attacks but vulnerable to malicious fine-tuning.
  arXiv  Detail & Related papers  (2024-08-04T13:59:09Z)
• Certifiably Robust Image Watermark [57.546016845801134]
  Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns. We propose the first image watermarks with certified robustness guarantees against removal and forgery attacks.
  arXiv  Detail & Related papers  (2024-07-04T17:56:04Z)
• Watermark-based Attribution of AI-Generated Content [34.913290430783185]
  We conduct the first systematic study on watermark-based, user-level attribution of AI-generated content. Our key idea is to assign a unique watermark to each user of the GenAI service and embed this watermark into the AI-generated content created by that user. Attribution is then performed by identifying the user whose watermark best matches the one extracted from the given content.
  arXiv  Detail & Related papers  (2024-04-05T17:58:52Z)
• Safe and Robust Watermark Injection with a Single OoD Image [90.71804273115585]
  Training a high-performance deep neural network requires large amounts of data and computational resources. We propose a safe and robust backdoor-based watermark injection technique. We induce random perturbation of model parameters during watermark injection to defend against common watermark removal attacks.
  arXiv  Detail & Related papers  (2023-09-04T19:58:35Z)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)
• A Watermark for Large Language Models [84.95327142027183]
  We propose a watermarking framework for proprietary language models. The watermark can be embedded with negligible impact on text quality. It can be detected using an efficient open-source algorithm without access to the language model API or parameters.
  arXiv  Detail & Related papers  (2023-01-24T18:52:59Z)

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.