SOURCE-LINKED INTELLIGENCE

On the Information-Theoretic Limits of Latent-Space Watermarking Through Pretrained Generators

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

We study latent-space watermarking through a pretrained generator using a prescribed latent-to-output stochastic mapping, called the renderer. A watermark encoder selects the latent input using a message and secret key. For every message and semantic context, the released output must have exactly the desired conditional output distribution. For finite alphabets, we derive rate--key inner and outer bounds and characterize the coding and coordination requirements for realizing watermark communication through the prescribed latent interface. When the target output distribution of the generator un

Read original source ↗ Open in workspace

recordType

paper

region

Global