# Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models Source: [Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:37:39.153Z Authors: Peifei Zhu, Tsubasa Takahashi, Hirokatsu Kataoka Published: 2024-04-15T01:27:07.000Z ## Abstract Diffusion Models (DMs) have shown remarkable capabilities in various image-generation tasks. However, there are growing concerns that DMs could be used to imitate unauthorized creations and thus raise copyright issues. To address this issue, we propose a novel framework that embeds personal watermarks in the generation of adversarial examples. Such examples can force DMs to generate images with visible watermarks and prevent DMs from imitating unauthorized images. We construct a generator based on conditional adversarial networks and design three losses (adversarial loss, GAN loss, and perturbation loss) to generate adversarial examples that have subtle perturbation but can effectively attack DMs to prevent copyright violations. Training a generator for a personal watermark by our method only requires 5-10 samples within 2-3 minutes, and once the generator is trained, it can generate adversarial examples with that watermark significantly fast (0.2s per image). We conduct extensive experiments in various conditional image-generation scenarios. Compared to existing methods that generate images with chaotic textures, our method adds visible watermarks on the generated images, which is a more straightforward way to indicate copyright violations. We also observe that our adversarial examples exhibit good transferability across unknown generative models. Therefore, this work provides a simple yet powerful way to protect copyright from DM-based imitation. ## 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. - [Synthetic-output protection on WikiArt Textual Inversion route (synthetic-output)](): Synthetic-output protection; WikiArt Textual Inversion route (synthetic-output); CSD: 0.439. - [Synthetic-output protection on WikiArt DreamBooth route (synthetic-output)](): Synthetic-output protection; WikiArt DreamBooth route (synthetic-output); CSD: 0.628. - [Image Watermarking on WikiArt](): Image Watermarking; WikiArt; Cheng20 Distance: 0.485. ## Original sources and implementation [Original paper]() [PDF]()