Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models

TL;DR

This paper introduces a watermark-embedding framework for adversarial examples that effectively prevents diffusion models from generating unauthorized images, offering a practical solution for copyright protection.

Contribution

It proposes a novel generator-based method to embed visible watermarks into adversarial examples, enabling quick training and fast generation for copyright enforcement against diffusion models.

Findings

Watermarked adversarial examples effectively prevent diffusion models from copying images.

The method requires only 5-10 samples for training and generates examples in 0.2 seconds.

The approach shows good transferability across different generative models.

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.