Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space
Top Cited Papers
- 27 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 3399-3410
Abstract
Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of image quality and watermark robustness. Watermarks with superior image quality usually have inferior robustness against attacks such as blurring and JPEG compression, while watermarks with superior robustness usually significantly damage image quality. This dilemma stems from the traditional paradigm where watermarks are injected and detected in pixel space, relying on pixel perturbation for watermark detection and resilience against attacks. In this paper, we highlight that an effective solution to the problem is to both inject and detect watermarks in the latent diffusion space, and propose Latent Watermark with a progressive training strategy. It weakens the direct connection between quality and robustness and thus alleviates their contradiction. We conduct evaluations on two datasets and against 10 watermark attacks. Six metrics measure the image quality and watermark robustness. Results show that compared to the recently proposed methods such as StableSignature, StegaStamp, RoSteALS, LaWa, TreeRing, and DiffuseTrace, LW not only surpasses them in terms of robustness but also offers superior image quality. Our code will be available at https://github.com/RichardSunnyMeng/LatentWatermark.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2021YFC3320103)
- National Natural Science Foundation of China (62272460)
- Beijing Natural Science Foundation (4232037)
This publication has 28 references indexed in Scilit:
- LaWa: Using Latent Space for In-Generation Image Watermarking2024
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Vector Quantized Diffusion Model for Text-to-Image Synthesis2022
- What Makes Fake Images Detectable? Understanding Properties that Generalize2020
- Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues2020
- Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention Modules2020
- StegaStamp: Invisible Hyperlinks in Physical Photographs2020
- CNN-Generated Images Are Surprisingly Easy to Spot… for Now2020
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Microsoft COCO: Common Objects in Context2014