# Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image

Source: [Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image](<https://www.sota2.com/research/paper/68fa78421e209131cea7775f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:34:18.624Z

Authors: Anubhav Jain, Yuya Kobayashi, Naoki Murata, Yuhta Takida, Takashi Shibuya, Yuki Mitsufuji, Niv Cohen, Nasir Memon, Julian Togelius

Published: 2025-04-27T18:29:26.000Z

## Abstract

Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embed a secret key in the initial noise. The resulting pattern is often considered hard to remove and forge into unrelated images. In this paper, we propose a black-box adversarial attack without presuming access to the diffusion model weights. Our attack uses only a single watermarked example and is based on a simple observation: there is a many-to-one mapping between images and initial noises. There are regions in the clean image latent space pertaining to each watermark that get mapped to the same initial noise when inverted. Based on this intuition, we propose an adversarial attack to forge the watermark by introducing perturbations to the images such that we can enter the region of watermarked images. We show that we can also apply a similar approach for watermark removal by learning perturbations to exit this region. We report results on multiple watermarking schemes (Tree-Ring, RingID, WIND, and Gaussian Shading) across two diffusion models (SDv1.4 and SDv2.0). Our results demonstrate the effectiveness of the attack and expose vulnerabilities in the watermarking methods, motivating future research on improving them.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Quality Assessment on Diffusion-based Watermarked Images](<https://www.sota2.com/research/sota/image-quality-assessment-on-diffusion-based-watermarked-images.md>): Image Quality Assessment; Diffusion-based Watermarked Images; CLIP Score: 31.356.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.20111>)

[PDF](<https://arxiv.org/pdf/2504.20111.pdf>)
