mlsanityData to 14 Oct 2026

Hey That's Mine Imperceptible Watermarks are Preserved in Diffusion Generated Outputs

arXiv 2308.11123 ↗First posted 22 Aug 2023cs.MM cs.CV eess.IVcited by 3

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

Generative models have seen an explosion in popularity with the release of huge generative Diffusion models like Midjourney and Stable Diffusion to the public. Because of this new ease of access, questions surrounding the automated collection of data and issues regarding content ownership have started to build. In this paper we present new work which aims to provide ways of protecting content when shared to the public. We show that a generative Diffusion model trained on data that has been imperceptibly watermarked will generate new images with these watermarks present. We further show that if a given watermark is correlated with a certain feature of the training data, the generated images will also have this correlation. Using statistical tests we show that we are able to determine whether a model has been trained on marked data, and what data was marked. As a result our system offers a solution to protect intellectual property when sharing content online.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 26 of its 31 references that are in the map. First posted on arXiv 22 Aug 2023.

Builds on

26 of 31 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Process6 Jun
  2. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust31 May
  3. 2023Watermarking Diffusion Model21 May
  4. 2023Generative Steganography Diffusion5 May
  5. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models27 Mar
  6. 2023A Recipe for Watermarking Diffusion Models17 Mar
  7. 2023Extracting Training Data from Diffusion Models30 Jan

Other references · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  9. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 628
  10. 2020Backdoor Learning: A Surveycited by 426
  11. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 276
  12. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 201
7 more
  1. 2021Conditional Image Generation with Score-Based Diffusion Modelscited by 197
  2. 2023Foundation Models and Fair Usecited by 116
  3. 2021A survey of deep neural network watermarking techniquescited by 73
  4. 2019SteganoGAN: High Capacity Image Steganography with GANscited by 72
  5. 2020Radioactive data: tracing through trainingcited by 67
  6. 2023Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarkingcited by 37
  7. 2023Low-frequency Image Deep Steganography: Manipulate the Frequency Distribution to Hide Secrets with Tenacious Robustnesscited by 3

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimizationcited by 46
  2. 2024MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retrainingcited by 5
  3. 2024Hidden Echoes Survive Training in Audio To Audio Generative Instrument Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Image Watermarking of Generative Diffusion Models
  2. 2025Spread them Apart: Towards Robust Watermarking of Generated Content
  3. 2024Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage
  4. 2024A Watermark-Conditioned Diffusion Model for IP Protection
  5. 2024Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection
  6. 2023DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
  7. 2025Dynamic watermarks in images generated by diffusion models
  8. 2025Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models