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

TL;DR

This paper introduces a two-stage, distortion-free image watermarking method using diffusion models and Fourier patterns, achieving high robustness against forgery and removal attacks to help identify AI-generated images.

Contribution

It presents a novel two-stage watermarking framework that enhances detection efficiency and robustness, addressing vulnerabilities of previous methods.

Findings

Achieves state-of-the-art robustness to forgery attacks

Effectively detects watermarks in generated images

Maintains image quality without distortion

Abstract

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.