ZK-WAGON: Imperceptible Watermark for Image Generation Models using ZK-SNARKs

• URL: http://arxiv.org/abs/2510.01967v1
• Date: Thu, 02 Oct 2025 12:39:57 GMT
• Title: ZK-WAGON: Imperceptible Watermark for Image Generation Models using ZK-SNARKs
• Authors: Aadarsh Anantha Ramakrishnan, Shubham Agarwal, Selvanayagam S, Kunwar Singh,
• Abstract summary: ZK-WAGON is a novel system for watermarking image generation models using the Zero-Knowledge Succinct Non Interactive Argument of Knowledge (ZK-SNARKs)<n>Our approach enables verifiable proof of origin without exposing model weights, generation prompts, or any sensitive internal information.<n>We demonstrate this system on both GAN and Diffusion models, providing a secure, model-agnostic pipeline for trustworthy AI image generation.
• Score: 4.084465411494742
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: As image generation models grow increasingly powerful and accessible, concerns around authenticity, ownership, and misuse of synthetic media have become critical. The ability to generate lifelike images indistinguishable from real ones introduces risks such as misinformation, deepfakes, and intellectual property violations. Traditional watermarking methods either degrade image quality, are easily removed, or require access to confidential model internals - making them unsuitable for secure and scalable deployment. We are the first to introduce ZK-WAGON, a novel system for watermarking image generation models using the Zero-Knowledge Succinct Non Interactive Argument of Knowledge (ZK-SNARKs). Our approach enables verifiable proof of origin without exposing model weights, generation prompts, or any sensitive internal information. We propose Selective Layer ZK-Circuit Creation (SL-ZKCC), a method to selectively convert key layers of an image generation model into a circuit, reducing proof generation time significantly. Generated ZK-SNARK proofs are imperceptibly embedded into a generated image via Least Significant Bit (LSB) steganography. We demonstrate this system on both GAN and Diffusion models, providing a secure, model-agnostic pipeline for trustworthy AI image generation.

Related papers

• NWaaS: Nonintrusive Watermarking as a Service for X-to-Image DNN [15.803288210824796]
  Deep neural network (DNN) models can be protected with watermarking.<n>Current methods are inherently intrusive as they modify the model parameters or alter the structure.<n>We introduce Nondefined Watermarking as a Service (NW), a novel trustless paradigm designed for X-to-Image models.<n>NW addresses deployment challenges by establishing a robust and nonintrusive side channel in the protected model's black-box API.
  arXiv  Detail & Related papers  (2025-07-24T02:07:28Z)
• 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)
• 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)
• 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)
• RoboSignature: Robust Signature and Watermarking on Network Attacks [0.5461938536945723]
  We present a novel adversarial fine-tuning attack that disrupts the model's ability to embed the intended watermark.<n>Our findings emphasize the importance of anticipating and defending against potential vulnerabilities in generative systems.
  arXiv  Detail & Related papers  (2024-12-22T04:36:27Z)
• Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending [54.26862913139299]
  We introduce a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB)<n> TEAWIB incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models.<n>Experiments validate the effectiveness of TEAWIB, showcasing the state-of-the-art performance in perceptual quality and attribution accuracy.
  arXiv  Detail & Related papers  (2024-09-17T07:52:09Z)
• Protect-Your-IP: Scalable Source-Tracing and Attribution against Personalized Generation [19.250673262185767]
  We propose a unified approach for image copyright source-tracing and attribution. We introduce an innovative watermarking-attribution method that blends proactive and passive strategies. We have conducted experiments using various celebrity portrait series sourced online.
  arXiv  Detail & Related papers  (2024-05-26T15:14:54Z)
• How to Trace Latent Generative Model Generated Images without Artificial Watermark? [88.04880564539836]
  Concerns have arisen regarding potential misuse related to images generated by latent generative models. We propose a latent inversion based method called LatentTracer to trace the generated images of the inspected model. Our experiments show that our method can distinguish the images generated by the inspected model and other images with a high accuracy and efficiency.
  arXiv  Detail & Related papers  (2024-05-22T05:33:47Z)
• 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)

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.