TokenTrace：通过水印令牌恢复实现多概念归因
TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery
提出一种在扩散模型生成过程中嵌入语义水印的主动防御框架，通过同时扰动文本提示词嵌入和初始潜变量噪声，并设计基于查询的TokenTrace模块，实现从单张生成图像中解耦并独立验证多个概念（如物体和风格）的归属，为生成内容的版权追溯和概念级归因提供了可复用的技术方案。
原文依据 we introduce TokenTrace, a novel proactive watermarking framework for robust, multi-concept attribution.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成式AI模型对知识产权（IP）构成了重大挑战，因为它们能够复制独特的艺术风格和概念而不进行归属。尽管水印提供了一种潜在的解决方案，但现有方法在复杂场景下往往失效，即当多个概念（例如一个物体和一种艺术风格）组合在单张图像中时。这些方法难以对每个概念进行解耦和独立归因。在本工作中，我们提出了TokenTrace，一种新颖的主动水印框架，用于鲁棒的多概念归因。我们的方法通过同时扰动引导扩散模型生成过程的文本提示词嵌入和初始潜变量噪声，将秘密签名嵌入到语义域中。对于检索，我们提出了一种基于查询的TokenTrace模块，该模块以生成图像和指定需要检索哪些概念（例如特定物体或风格）的文本查询作为输入。这种基于查询的机制使得该模块能够从单张生成图像中解耦并独立验证多个概念的存在。大量实验表明，我们的方法在单概念（物体和风格）和多概念归因任务上均达到了最优性能，显著优于现有基线，同时保持了高视觉质量和对常见变换的鲁棒性。
英文原文摘要 1391 字符
Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in complex scenarios where multiple concepts (e.g., an object and an artistic style) are composed within a single image. These methods struggle to disentangle and attribute each concept individually. In this work, we introduce TokenTrace, a novel proactive watermarking framework for robust, multi-concept attribution. Our method embeds secret signatures into the semantic domain by simultaneously perturbing the text prompt embedding and the initial latent noise that guide the diffusion model's generation process. For retrieval, we propose a query-based TokenTrace module that takes the generated image and a textual query specifying which concepts need to be retrieved (e.g., a specific object or style) as inputs. This query-based mechanism allows the module to disentangle and independently verify the presence of multiple concepts from a single generated image. Extensive experiments show that our method achieves state-of-the-art performance on both single-concept (object and style) and multi-concept attribution tasks, significantly outperforming existing baselines while maintaining high visual quality and robustness to common transformations.