隱藏在噪音中：圖像的兩階段強健浮水印技術

摘要

隨著影像生成器的品質不斷提高，Deepfakes 已成為一個引起社會廣泛討論的話題。影像浮水印技術讓負責的模型擁有者能夠檢測並標記其由人工智慧生成的內容，進而減輕損害。然而，目前在影像浮水印技術方面的最先進方法仍然容易受到偽造和移除攻擊的影響。這種弱點部分原因在於浮水印會扭曲生成的影像分佈，無意中透露了有關浮水印技術的信息。在這項研究中，我們首先展示了一種基於擴散模型初始噪聲的無失真浮水印方法。然而，檢測浮水印需要將為一幅影像重建的初始噪聲與先前使用的所有初始噪聲進行比較。為了減輕這些問題，我們提出了一種兩階段浮水印框架以實現高效的檢測。在生成過程中，我們利用生成的傅立葉模式來擴充初始噪聲，以嵌入有關我們使用的初始噪聲組的信息。在檢測過程中，我們 (i) 檢索相關的噪聲組，並 (ii) 在給定組中尋找可能與我們的影像匹配的初始噪聲。這種浮水印方法實現了對偽造和移除的最先進抵抗能力，抵禦了各種攻擊。

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.

隱藏在噪音中：圖像的兩階段強健浮水印技術

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

摘要

Summary

Support