Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models

• URL: http://arxiv.org/abs/2311.04378v4
• Date: Tue, 23 Jul 2024 18:05:59 GMT
• Title: Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
• Authors: Hanlin Zhang, Benjamin L. Edelman, Danilo Francati, Daniele Venturi, Giuseppe Ateniese, Boaz Barak,
• Abstract summary: A strong watermarking scheme satisfies the property that a computationally bounded attacker cannot erase the watermark without causing significant quality degradation. We prove that, under well-specified and natural assumptions, strong watermarking is impossible to achieve.
• Score: 19.29349934856703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property that a computationally bounded attacker cannot erase the watermark without causing significant quality degradation. In this paper, we study the (im)possibility of strong watermarking schemes. We prove that, under well-specified and natural assumptions, strong watermarking is impossible to achieve. This holds even in the private detection algorithm setting, where the watermark insertion and detection algorithms share a secret key, unknown to the attacker. To prove this result, we introduce a generic efficient watermark attack; the attacker is not required to know the private key of the scheme or even which scheme is used. Our attack is based on two assumptions: (1) The attacker has access to a "quality oracle" that can evaluate whether a candidate output is a high-quality response to a prompt, and (2) The attacker has access to a "perturbation oracle" which can modify an output with a nontrivial probability of maintaining quality, and which induces an efficiently mixing random walk on high-quality outputs. We argue that both assumptions can be satisfied in practice by an attacker with weaker computational capabilities than the watermarked model itself, to which the attacker has only black-box access. Furthermore, our assumptions will likely only be easier to satisfy over time as models grow in capabilities and modalities. We demonstrate the feasibility of our attack by instantiating it to attack three existing watermarking schemes for large language models: Kirchenbauer et al. (2023), Kuditipudi et al. (2023), and Zhao et al. (2023). The same attack successfully removes the watermarks planted by all three schemes, with only minor quality degradation.

Related papers

• An undetectable watermark for generative image models [65.31658824274894]
  We present the first undetectable watermarking scheme for generative image models. In particular, an undetectable watermark does not degrade image quality under any efficiently computable metric. Our scheme works by selecting the initial latents of a diffusion model using a pseudorandom error-correcting code.
  arXiv  Detail & Related papers  (2024-10-09T18:33:06Z)
• 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)
• Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution [22.933101948176606]
  backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in released models. We design a new watermarking paradigm, $i.e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution.
  arXiv  Detail & Related papers  (2024-05-08T05:49:46Z)
• Unbiased Watermark for Large Language Models [67.43415395591221]
  This study examines how significantly watermarks impact the quality of model-generated outputs. It is possible to integrate watermarks without affecting the output probability distribution. The presence of watermarks does not compromise the performance of the model in downstream tasks.
  arXiv  Detail & Related papers  (2023-09-22T12:46:38Z)
• Towards Robust Model Watermark via Reducing Parametric Vulnerability [57.66709830576457]
  backdoor-based ownership verification becomes popular recently, in which the model owner can watermark the model. We propose a mini-max formulation to find these watermark-removed models and recover their watermark behavior. Our method improves the robustness of the model watermarking against parametric changes and numerous watermark-removal attacks.
  arXiv  Detail & Related papers  (2023-09-09T12:46:08Z)
• 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)
• Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networks [22.614495877481144]
  State-of-the-art trigger set-based watermarking algorithms do not achieve their designed goal of proving ownership. We propose novel adaptive attacks that harness the adversary's knowledge of the underlying watermarking algorithm of a target model.
  arXiv  Detail & Related papers  (2021-06-18T14:23:55Z)
• 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.