Spread them Apart: Towards Robust Watermarking of Generated Content
This addresses ethical concerns about ownership claims on generated content, offering a practical solution for users of generative models, though it is incremental as it builds on existing watermarking methods.
The paper tackles the problem of distinguishing AI-generated images from real ones by embedding watermarks during model inference, proving robustness against bounded perturbations and matching state-of-the-art schemes in synthetic attack resistance.
Generative models that can produce realistic images have improved significantly in recent years. The quality of the generated content has increased drastically, so sometimes it is very difficult to distinguish between the real images and the generated ones. Such an improvement comes at a price of ethical concerns about the usage of the generative models: the users of generative models can improperly claim ownership of the generated content protected by a license. In this paper, we propose an approach to embed watermarks into the generated content to allow future detection of the generated content and identification of the user who generated it. The watermark is embedded during the inference of the model, so the proposed approach does not require the retraining of the latter. We prove that watermarks embedded are guaranteed to be robust against additive perturbations of a bounded magnitude. We apply our method to watermark diffusion models and show that it matches state-of-the-art watermarking schemes in terms of robustness to different types of synthetic watermark removal attacks.