Introduces a sketch-based watermarking method for masked diffusion language models providing an order-agnostic detection statistic decoupled from local context.
arXiv preprint arXiv:2411.11434 , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Global Sketch-Based Watermarking for Diffusion Language Models
Introduces a sketch-based watermarking method for masked diffusion language models providing an order-agnostic detection statistic decoupled from local context.