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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Arabi, Kasra, Feuer, Benjamin, Witter, R. Teal, Hegde, Chinmay, Cohen, Niv
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908339104907264
author Arabi, Kasra
Feuer, Benjamin
Witter, R. Teal
Hegde, Chinmay
Cohen, Niv
author_facet Arabi, Kasra
Feuer, Benjamin
Witter, R. Teal
Hegde, Chinmay
Cohen, Niv
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04653
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hidden in the Noise: Two-Stage Robust Watermarking for Images
Arabi, Kasra
Feuer, Benjamin
Witter, R. Teal
Hegde, Chinmay
Cohen, Niv
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title Hidden in the Noise: Two-Stage Robust Watermarking for Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.04653