Artificial Intelligence Generated Content (AIGC) is gaining great popularity
in social media, with many commercial services available. These services
leverage advanced generative models, such as latent diffusion models and large
language models, to generate creative content (e.g., realistic images, fluent
sentences) for users. The usage of such generated content needs to be highly
regulated, as the service providers need to ensure the users do not violate the
usage policies (e.g., abuse for commercialization, generating and distributing
unsafe content).
Numerous watermarking approaches have been proposed recently. However, in
this paper, we show that an adversary can easily break these watermarking
mechanisms. Specifically, we consider two possible attacks. (1) Watermark
removal: the adversary can easily erase the embedded watermark from the
generated content and then use it freely without the regulation of the service
provider. (2) Watermark forge: the adversary can create illegal content with
forged watermarks from another user, causing the service provider to make wrong
attributions. We propose WMaGi, a unified framework to achieve both attacks in
a holistic way. The key idea is to leverage a pre-trained diffusion model for
content processing, and a generative adversarial network for watermark removing
or forging. We evaluate WMaGi on different datasets and embedding setups. The
results prove that it can achieve high success rates while maintaining the
quality of the generated content. Compared with existing diffusion model-based
attacks, WMaGi is 5,050$\sim$11,000$\times$ faster.

人工智能生成内容 (AIGC) 在社交媒体上越来越受欢迎，其服务利用先进的生成模型，如潜在扩散模型和大型语言模型，为用户生成创意内容 (例如逼真的图像，流畅的句子)。本文展示了水印在生成的内容中的易破解性，并提出了 WMaGi 框架，通过利用预训练的扩散模型和生成对抗网络实现水印的移除和伪造，从而实现对生成内容的高速攻击。