嵌入在噪声中：面向图像的两阶段鲁棒水印技术

摘要

随着图像生成器质量不断提高，深度伪造成为一个备受社会关注的话题。图像水印技术使负责任的模型所有者能够检测和标记其由人工智能生成的内容，从而有助于减轻伤害。然而，当前图像水印技术的最新方法仍然容易受到伪造和移除攻击的影响。这种脆弱性部分原因在于水印会扭曲生成图像的分布，无意中透露了有关水印技术的信息。在这项工作中，我们首先展示了一种基于扩散模型初始噪声的无失真水印方法用于图像。然而，检测水印需要将为图像重建的初始噪声与先前使用的所有初始噪声进行比较。为了减轻这些问题，我们提出了一个两阶段的高效检测水印框架。在生成过程中，我们利用生成的傅立叶模式来增强初始噪声，以嵌入有关我们使用的初始噪声组的信息。在检测阶段，我们（i）检索相关的噪声组，并（ii）在给定的组内搜索可能与我们的图像匹配的初始噪声。这种水印方法在抵御各种攻击方面取得了最先进的防伪和去除效果。

English

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.

嵌入在噪声中：面向图像的两阶段鲁棒水印技术

Hidden in the Noise: Two-Stage Robust Watermarking for Images

摘要

Summary

Support