In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the imperative for robust intellectual property protection. Current protection strategies either employ backdoor-based methods, integrating a watermark task as a simpler training objective with the main model task, or embedding watermarks directly into the final output samples. However, the former approach is fragile compared to existing backdoor defense techniques, while the latter fundamentally alters the expected output. In this work, we introduce a novel watermarking framework by embedding the watermark into the whole diffusion process, and theoretically ensure that our final output samples contain no additional information. Furthermore, we utilize statistical algorithms to verify the watermark from internally generated model samples without necessitating triggers as conditions. Detailed theoretical analysis and experimental validation demonstrate the effectiveness of our proposed method.

翻译：在实际应用中，扩散模型的广泛部署通常需要大量的训练投入。随着扩散模型的应用日益多样化，对其潜在滥用的担忧凸显了实施稳健知识产权保护的迫切性。现有的保护策略要么采用基于后门的方法，将水印任务作为更简单的训练目标与主模型任务相结合，要么直接将水印嵌入最终输出样本中。然而，前者相较于现有的后门防御技术较为脆弱，而后者从根本上改变了预期输出。在本工作中，我们提出了一种新颖的水印框架，通过将水印嵌入整个扩散过程，并从理论上确保最终输出样本不包含额外信息。此外，我们利用统计算法从模型内部生成的样本中验证水印，而无需以触发器作为条件。详细的理论分析和实验验证证明了我们提出方法的有效性。