在生成模型隐空间嵌入水印，实现高效无痕的图像版权保护。
Learning to Watermark in the Latent Space of Generative Models
- 在隐空间训练水印模型，避免像素级处理带来的计算开销。
- 相比像素空间方法，速度提升20倍，且视觉失真更小。
- 可将水印能力蒸馏到生成模型中，适合大规模内容审核场景。
现有图像生成水印方法多依赖像素空间的后期处理，带来计算开销和视觉伪影。本文探索隐空间水印，提出统一框架DistSeal，适用于扩散模型与自回归模型。通过在生成模型隐空间训练后置水印器，可将其有效蒸馏至生成模型或隐空间解码器，实现模型内水印。结果表明，隐空间水印具备良好鲁棒性，同时保持相似的不可察觉性，并相比像素空间基线提速达20倍。实验进一步显示，隐空间水印蒸馏效果优于像素空间，提供更高效、更鲁棒的解决方案。
原文摘要 · Abstract (English)
Existing approaches for watermarking AI-generated images often rely on post-hoc methods applied in pixel space, introducing computational overhead and potential visual artifacts. In this work, we explore latent space watermarking and introduce DistSeal, a unified approach for latent watermarking that works across both diffusion and autoregressive models. Our approach works by training post-hoc watermarking models in the latent space of generative models. We demonstrate that these latent watermarkers can be effectively distilled either into the generative model itself or into the latent decoder, enabling in-model watermarking. The resulting latent watermarks achieve competitive robustness while offering similar imperceptibility and up to 20x speedup compared to pixel-space baselines. Our experiments further reveal that distilling latent watermarkers outperforms distilling pixel-space ones, providing a solution that is both more efficient and more robust.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。