The ethical need to protect AI-generated content has been a significant concern in recent years. While existing watermarking strategies have demonstrated success in detecting synthetic content (detection), there has been limited exploration in identifying the users responsible for generating these outputs from a single model (owner identification). In this paper, we focus on both practical scenarios and propose a unified watermarking framework for content copyright protection within the context of diffusion models. Specifically, we consider two parties: the model provider, who grants public access to a diffusion model via an API, and the users, who can solely query the model API and generate images in a black-box manner. Our task is to embed hidden information into the generated contents, which facilitates further detection and owner identification. To tackle this challenge, we propose a Watermark-conditioned Diffusion model called WaDiff, which manipulates the watermark as a conditioned input and incorporates fingerprinting into the generation process. All the generative outputs from our WaDiff carry user-specific information, which can be recovered by an image extractor and further facilitate forensic identification. Extensive experiments are conducted on two popular diffusion models, and we demonstrate that our method is effective and robust in both the detection and owner identification tasks. Meanwhile, our watermarking framework only exerts a negligible impact on the original generation and is more stealthy and efficient in comparison to existing watermarking strategies.

翻译：近年来，保护人工智能生成内容的伦理需求已成为重要关切。尽管现有水印策略在检测合成内容（检测任务）方面已取得成功，但在从单一模型中识别生成这些输出的责任用户（所有者识别）方面探索有限。本文聚焦于两种实际应用场景，提出一个统一的扩散模型内容版权保护水印框架。具体而言，我们考虑两方参与者：通过API公开提供扩散模型的模型提供商，以及仅能以黑盒方式查询模型API并生成图像的用户。我们的任务是在生成内容中嵌入隐藏信息，以促进后续检测和所有者识别。为应对这一挑战，我们提出一种名为WaDiff的水印条件扩散模型，该模型将水印作为条件输入进行调控，并将指纹特征融入生成过程。我们WaDiff模型的所有生成输出都携带用户特定信息，这些信息可通过图像提取器恢复，并进一步助力溯源识别。我们在两种主流扩散模型上进行了大量实验，证明我们的方法在检测和所有者识别任务中均具有效性和鲁棒性。同时，与现有水印策略相比，我们的水印框架对原始生成质量影响可忽略不计，且具有更强的隐蔽性和更高的效率。