标题： MaXsive：扩散模型中高容量和鲁棒的无训练生成图像水印技术 显示英文标题

标题： MaXsive: High-Capacity and Robust Training-Free Generative Image Watermarking in Diffusion Models

摘要： 扩散模型在图像合成中的巨大成功导致了巨型商业模型的发布，引发了版权保护和不当内容生成的问题。 无需训练的扩散水印提供了解决这些问题的低成本方案。 然而，之前的工作仍然容易受到旋转、缩放和平移（RST）攻击。 尽管一些方法采用了精心设计的模式来缓解这个问题，但它们通常会降低水印容量，这可能导致身份（ID）共谋。 为了解决这些问题，我们提出了MaXsive，一种无需训练的扩散模型生成水印技术，具有高容量和鲁棒性。 MaXsive充分利用初始噪声来对扩散模型进行水印。 此外，我们提出注入X形模板以恢复RST失真，而不是使用精心重复的环形模式。 这种设计显著提高了鲁棒性而不会损失任何容量，使得ID共谋更不容易发生。 MaXsive的有效性已在验证和识别场景下的两个知名水印基准测试中得到验证。 显示英文摘要

摘要： The great success of the diffusion model in image synthesis led to the release of gigantic commercial models, raising the issue of copyright protection and inappropriate content generation. Training-free diffusion watermarking provides a low-cost solution for these issues. However, the prior works remain vulnerable to rotation, scaling, and translation (RST) attacks. Although some methods employ meticulously designed patterns to mitigate this issue, they often reduce watermark capacity, which can result in identity (ID) collusion. To address these problems, we propose MaXsive, a training-free diffusion model generative watermarking technique that has high capacity and robustness. MaXsive best utilizes the initial noise to watermark the diffusion model. Moreover, instead of using a meticulously repetitive ring pattern, we propose injecting the X-shape template to recover the RST distortions. This design significantly increases robustness without losing any capacity, making ID collusion less likely to happen. The effectiveness of MaXsive has been verified on two well-known watermarking benchmarks under the scenarios of verification and identification.