A Somewhat Robust Image Watermark against Diffusion-based Editing Models

Mingtian Tan, Tianhao Wang, Somesh Jha
11/22/2023
cs.CRcs.CVcs.LG

Official code: BennyTMT/RIW (1 star, last commit 2024-09-12).

Abstract

Recently, diffusion models (DMs) have become the state-of-the-art method for image synthesis. Editing models based on DMs, known for their high fidelity and precision, have inadvertently introduced new challenges related to image copyright infringement and malicious editing. Our work is the first to formalize and address this issue. After assessing and attempting to enhance traditional image watermarking techniques, we recognize their limitations in this emerging context. In response, we develop a novel technique, RIW (Robust Invisible Watermarking), to embed invisible watermarks leveraging adversarial example techniques. Our technique ensures a high extraction accuracy of $96\%$ for the invisible watermark after editing, compared to the $0\%$ offered by conventional methods. We provide access to our code at https://github.com/BennyTMT/RIW.

View on arXivView PDF

Code Implementations(1)

BennyTMT/RIWOfficial
10PythonOct 18, 20232 years ago

Similar Papers

Dynamic watermarks in images generated by diffusion models

90% match2025

A Recipe for Watermarking Diffusion Models

89% match1 repo1522023

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

88% match2 repos1422026

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models

88% match1 repo252024

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models

88% match1 repo252024

SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models

87% match2025

Cite this paper

@article{tan2023somewhat,
  title  = {A Somewhat Robust Image Watermark against Diffusion-based Editing Models},
  author = {Mingtian Tan and Tianhao Wang and Somesh Jha},
  year   = {2023},
  eprint = {2311.13713},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.13713v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.13713.svg)](https://codeofpaper.com/paper/2311.13713)

Discussion