As the quality of image generators continues to improve, deepfakes become a topic of considerable societal debate. Image watermarking allows responsible model owners to detect and label their AI-generated content, which can mitigate the harm. Yet, current state-of-the-art methods in image watermarking remain vulnerable to forgery and removal attacks. This vulnerability occurs in part because watermarks distort the distribution of generated images, unintentionally revealing information about the watermarking techniques. In this work, we first demonstrate a distortion-free watermarking method for images, based on a diffusion model's initial noise. However, detecting the watermark requires comparing the initial noise reconstructed for an image to all previously used initial noises. To mitigate these issues, we propose a two-stage watermarking framework for efficient detection. During generation, we augment the initial noise with generated Fourier patterns to embed information about the group of initial noises we used. For detection, we (i) retrieve the relevant group of noises, and (ii) search within the given group for an initial noise that might match our image. This watermarking approach achieves state-of-the-art robustness to forgery and removal against a large battery of attacks.

翻译：随着图像生成器质量的持续提升，深度伪造已成为引发广泛社会讨论的话题。图像水印技术使得负责任的模型所有者能够检测并标记其AI生成的内容，从而减轻潜在危害。然而，当前最先进的图像水印方法仍易受到伪造和移除攻击。这种脆弱性部分源于水印会扭曲生成图像的分布，无意中泄露了水印技术的信息。在本研究中，我们首先提出一种基于扩散模型初始噪声的无失真图像水印方法。然而，检测水印需要将图像重建的初始噪声与所有先前使用过的初始噪声进行比对。为解决这一问题，我们提出一种高效检测的两阶段水印框架。在生成阶段，我们通过生成的傅里叶模式增强初始噪声，以嵌入所用初始噪声组的信息。在检测阶段，我们（i）检索相关噪声组，并（ii）在给定组内搜索可能与图像匹配的初始噪声。该水印方法在面对多种攻击时，实现了当前最优的防伪造与抗移除鲁棒性。