# Watermarking Discrete Diffusion Language Models

arXiv: https://arxiv.org/abs/2511.02083 · HTML: https://mlsanity.com/paper/2511.02083/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 3 Nov 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 30 of 36)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [Mercury: Ultra-Fast Language Models Based on Diffusion](https://mlsanity.com/paper/2506.17298/) (2025)
- [Undetectable Watermarks for Language Models](https://mlsanity.com/paper/2306.09194/) (2023)
- [SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control](https://mlsanity.com/paper/2210.17432/) (2022)
- [Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust](https://mlsanity.com/paper/2305.20030/) (2023)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [Simple Guidance Mechanisms for Discrete Diffusion Models](https://mlsanity.com/paper/2412.10193/) (2024)
- [Concrete Score Matching: Generalized Score Matching for Discrete Data](https://mlsanity.com/paper/2211.00802/) (2022)
- [A Recipe for Watermarking Diffusion Models](https://mlsanity.com/paper/2303.10137/) (2023)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing](https://mlsanity.com/paper/2508.09192/) (2025)
- [Watermark Stealing in Large Language Models](https://mlsanity.com/paper/2402.19361/) (2024)
- [LaViDa: A Large Diffusion Language Model for Multimodal Understanding](https://mlsanity.com/paper/2505.16839/) (2025)
- [Publicly-Detectable Watermarking for Language Models](https://mlsanity.com/paper/2310.18491/) (2023)
- [A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules](https://mlsanity.com/paper/2404.01245/) (2024)
- [WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off](https://mlsanity.com/paper/2403.04808/) (2024)
- [ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization](https://mlsanity.com/paper/2411.03862/) (2024)
- [Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation](https://mlsanity.com/paper/2112.01799/) (2021)
- [WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models](https://mlsanity.com/paper/2311.07138/) (2023)

## Built on by (most cited first, 5 of 5)

- [dgMARK: Decoding-Guided Watermarking for Diffusion Language Models](https://mlsanity.com/paper/2601.22985/) (2026)
- [Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks](https://mlsanity.com/paper/2605.05503/) (2026)
- [Global Sketch-Based Watermarking for Diffusion Language Models](https://mlsanity.com/paper/2606.04486/) (2026)
- [SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields](https://mlsanity.com/paper/2608.20839/) (2026)
- [TANGO: Watermarking Masked Diffusion Language Models in Token Pairs](https://mlsanity.com/paper/2609.35224/) (2026)

## Abstract (arXiv)

Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language models (LLMs) and image diffusion models, it remains comparatively underexplored for discrete diffusion language models (DDLMs), which are becoming popular due to their high inference throughput. In this paper, we introduce one of the first watermarking methods for DDLMs. Our approach applies a distribution-preserving Gumbel-max sampling trick at every diffusion step and seeds the randomness by sequence position to enable reliable detection. We empirically demonstrate reliable detectability on LLaDA, a state-of-the-art DDLM. We also analytically prove that the watermark is distortion-free, with a false detection probability that decays exponentially in the sequence length. A key practical advantage is that our method realizes desired watermarking properties with no expensive hyperparameter tuning, making it straightforward to deploy and scale across models and benchmarks.