Introduces a sketch-based watermarking method for masked diffusion language models providing an order-agnostic detection statistic decoupled from local context.
arXiv preprint arXiv:2511.02083 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Chained rewrites by open-weight LLMs reduce watermark detection on diffusion LM outputs from 87.9% to 4.86% after five steps across multiple styles and models.
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.
-
Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks
Chained rewrites by open-weight LLMs reduce watermark detection on diffusion LM outputs from 87.9% to 4.86% after five steps across multiple styles and models.