Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models (2306.04642v4)

Published 25 May 2023 in cs.CR, cs.CV, and cs.LG

Abstract: Recently, Generative Diffusion Models (GDMs) have showcased their remarkable capabilities in learning and generating images. A large community of GDMs has naturally emerged, further promoting the diversified applications of GDMs in various fields. However, this unrestricted proliferation has raised serious concerns about copyright protection. For example, artists including painters and photographers are becoming increasingly concerned that GDMs could effortlessly replicate their unique creative works without authorization. In response to these challenges, we introduce a novel watermarking scheme, DiffusionShield, tailored for GDMs. DiffusionShield protects images from copyright infringement by GDMs through encoding the ownership information into an imperceptible watermark and injecting it into the images. Its watermark can be easily learned by GDMs and will be reproduced in their generated images. By detecting the watermark from generated images, copyright infringement can be exposed with evidence. Benefiting from the uniformity of the watermarks and the joint optimization method, DiffusionShield ensures low distortion of the original image, high watermark detection performance, and the ability to embed lengthy messages. We conduct rigorous and comprehensive experiments to show the effectiveness of DiffusionShield in defending against infringement by GDMs and its superiority over traditional watermarking methods. The code for DiffusionShield is accessible in https://github.com/Yingqiancui/DiffusionShield.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Feature purification: How adversarial training performs robust deep learning. In 2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS), pp.  977–988. IEEE, 2022.
  2. A latent variable model approach to pmi-based word embeddings. Transactions of the Association for Computational Linguistics, 4:385–399, 2016.
  3. Generalization of two-layer neural networks: An asymptotic viewpoint. In International conference on learning representations, 2019.
  4. Digital watermarking. Journal of Electronic Imaging, 11(3):414–414, 2002.
  5. Consistent diffusion models: Mitigating sampling drift by learning to be consistent. arXiv preprint arXiv:2302.09057, 2023.
  6. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp.  248–255. Ieee, 2009.
  7. Generative adversarial networks. Communications of the ACM, 63(11):139–144, 2020.
  8. Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. In European conference on computer vision, pp.  87–102. Springer, 2016.
  9. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  770–778, 2016.
  10. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598, 2022.
  11. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
  12. Ashwani Kumar. A review on implementation of digital image watermarking techniques using lsb and dwt. Information and Communication Technology for Sustainable Development: Proceedings of ICT4SD 2018, pp.  595–602, 2020.
  13. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083, 2017.
  14. Online learning for matrix factorization and sparse coding. Journal of Machine Learning Research, 11(1), 2010.
  15. Dwt-dct-svd based watermarking. In 2008 3rd International Conference on Communication Systems Software and Middleware and Workshops (COMSWARE’08), pp.  271–274. IEEE, 2008.
  16. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning, pp.  8162–8171. PMLR, 2021.
  17. Sparse coding with an overcomplete basis set: A strategy employed by v1? Vision research, 37(23):3311–3325, 1997.
  18. Justin N. M. Pinkney. Pokemon blip captions. https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions/, 2022.
  19. Digital watermarking: algorithms and applications. IEEE signal processing Magazine, 18(4):33–46, 2001.
  20. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 2022.
  21. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  10684–10695, 2022.
  22. Generating high fidelity data from low-density regions using diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  11492–11501, 2022.
  23. Combinational image watermarking in the spatial and frequency domains. Pattern Recognition, 36(4):969–975, 2003.
  24. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502, 2020.
  25. Stegastamp: Invisible hyperlinks in physical photographs. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  2117–2126, 2020.
  26. Don’t play favorites: Minority guidance for diffusion models. arXiv preprint arXiv:2301.12334, 2023.
  27. James Vincent. Ai art copyright lawsuit: Getty images and stable diffusion, February 2023. URL https://www.theverge.com/2023/2/6/23587393/ai-art-copyright-lawsuit-getty-images-stable-diffusion. Accessed: May 12, 2023.
  28. Diffusers: State-of-the-art diffusion models. https://github.com/huggingface/diffusers, 2022.
  29. High-capacity convolutional video steganography with temporal residual modeling. In Proceedings of the 2019 on international conference on multimedia retrieval, pp.  87–95, 2019.
  30. Watermarking neural networks with watermarked images. IEEE Transactions on Circuits and Systems for Video Technology, 31(7):2591–2601, 2020.
  31. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365, 2015.
  32. Artificial fingerprinting for generative models: Rooting deepfake attribution in training data. In Proceedings of the IEEE/CVF International conference on computer vision, pp.  14448–14457, 2021.
  33. Model watermarking for image processing networks. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pp.  12805–12812, 2020.
  34. Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543, 2023.
  35. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  586–595, 2018.
  36. Invisible steganography via generative adversarial networks. Multimedia tools and applications, 78:8559–8575, 2019.
  37. Proactive deepfake defence via identity watermarking. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp.  4602–4611, 2023a.
  38. A recipe for watermarking diffusion models. arXiv preprint arXiv:2303.10137, 2023b.
  39. Hidden: Hiding data with deep networks. In Proceedings of the European conference on computer vision (ECCV), pp.  657–672, 2018.
Citations (40)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - Yingqiancui/DiffusionShield (16 stars)