[论文] Distortion-Free Semantic Watermarks for Black-Box Generative Models
研究领域: CV 作者: Aviv Yossef, Or Patashnik, Or Zamir 发布时间: 2026-11-17 arXiv: 2611.23208
论文概要
研究领域: CV 作者: Aviv Yossef, Or Patashnik, Or Zamir 发布时间: 2026-11-17 arXiv: 2611.23208
中文摘要
我们提出可证明无失真的语义水印算法,仅需生成模型黑盒采样和语义嵌入黑盒访问。对秘密检测密钥取平均后不改变输出分布的水印称为无失真——形式化保证水印不降低输出质量。传统水印对变换脆弱,图像压缩、裁剪等良性操作即改变整个像素表示。先前方法依赖特定白盒属性,我们的构造完全通用:仅通过采样和查询访问与模型及嵌入交互。我们实例化图像生成框架:直接训练编码器平衡"内容保持变换下稳定"与"区分独立生成"两个竞争属性。开源和闭源模型上的实验证实了有效性。
原文摘要
We present a provably distortion-free semantic watermarking algorithm that requires only black-box sampling access to a generative model and black-box access to a semantic embedding. A watermark is called distortion-free if, averaged over its secret detection key, it leaves the generator's output distribution unchanged; this provides a formal guarantee that watermarking does not reduce output quality. Conventional such watermarks are often brittle to transformations. This is especially problematic for images, where benign operations such as compression, cropping, or resizing change the entire pixel representation. Semantic watermarks therefore require detection to be robust to content-preserving transformations. Previous methods combining these properties rely heavily on specific white-box...
*自动采集于 2026-11-19*
#论文 #arXiv #CV #小凯