# Dynamic watermarks in images generated by diffusion models

arXiv: https://arxiv.org/abs/2502.08927 · HTML: https://mlsanity.com/paper/2502.08927/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 19 of 19)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [What makes fake images detectable? Understanding properties that generalize](https://mlsanity.com/paper/2008.10588/) (2020)
- [Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust](https://mlsanity.com/paper/2305.20030/) (2023)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detection](https://mlsanity.com/paper/1703.04615/) (2017)
- [Supervised GAN Watermarking for Intellectual Property Protection](https://mlsanity.com/paper/2209.03466/) (2022)
- [CycleGANWM: A CycleGAN watermarking method for ownership verification](https://mlsanity.com/paper/2211.13737/) (2022)
- [A Convex Model for Edge-Histogram Specification with Applications to Edge-preserving Smoothing](https://mlsanity.com/paper/1806.08101/) (2018)
- [Image Watermarking of Generative Diffusion Models](https://mlsanity.com/paper/2502.10465/) (2025)

## Abstract (arXiv)

High-fidelity text-to-image diffusion models have revolutionized visual content generation, but their widespread use raises significant ethical concerns, including intellectual property protection and the misuse of synthetic media. To address these challenges, we propose a novel multi-stage watermarking framework for diffusion models, designed to establish copyright and trace generated images back to their source. Our multi-stage watermarking technique involves embedding: (i) a fixed watermark that is localized in the diffusion model's learned noise distribution and, (ii) a human-imperceptible, dynamic watermark in generates images, leveraging a fine-tuned decoder. By leveraging the Structural Similarity Index Measure (SSIM) and cosine similarity, we adapt the watermark's shape and color to the generated content while maintaining robustness. We demonstrate that our method enables reliable source verification through watermark classification, even when the dynamic watermark is adjusted for content-specific variations. Source model verification is enabled through watermark classification. o support further research, we generate a dataset of watermarked images and introduce a methodology to evaluate the statistical impact of watermarking on generated content.Additionally, we rigorously test our framework against various attack scenarios, demonstrating its robustness and minimal impact on image quality. Our work advances the field of AI-generated content security by providing a scalable solution for model ownership verification and misuse prevention.