# dgMARK: Decoding-Guided Watermarking for Diffusion Language Models

arXiv: https://arxiv.org/abs/2601.22985 · HTML: https://mlsanity.com/paper/2601.22985/

## Key facts

- Cited by 1 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 18 of its 66 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## 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, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models](https://mlsanity.com/paper/2505.19223/) (2025)
- [Mercury: Ultra-Fast Language Models Based on Diffusion](https://mlsanity.com/paper/2506.17298/) (2025)
- [LLaDA2.0: Scaling Up Diffusion Language Models to 100B](https://mlsanity.com/paper/2512.15745/) (2025)
- [A Survey on Diffusion Language Models](https://mlsanity.com/paper/2508.10875/) (2025)
- [Discrete Diffusion in Large Language and Multimodal Models: A Survey](https://mlsanity.com/paper/2506.13759/) (2025)
- [A Survey of Large Language Model Agents for Question Answering](https://mlsanity.com/paper/2503.19213/) (2025)
- [The Ethics of Interaction: Mitigating Security Threats in LLMs](https://mlsanity.com/paper/2401.12273/) (2024)
- [Targeted Phishing Campaigns using Large Scale Language Models](https://mlsanity.com/paper/2301.00665/) (2022)
- [Watermarking Discrete Diffusion Language Models](https://mlsanity.com/paper/2511.02083/) (2025)
- [DMark: Order-Agnostic Watermarking for Diffusion Large Language Models](https://mlsanity.com/paper/2510.02902/) (2025)
- [LR-DWM: Efficient Watermarking for Diffusion Language Models](https://mlsanity.com/paper/2601.12376/) (2026)
- [MirrorMark: Generalizable Mirrored Sampling for Multi-bit LLM Watermarking](https://mlsanity.com/paper/2601.22246/) (2026)

## Built on by (most cited first, 1 of 1)

- [SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields](https://mlsanity.com/paper/2608.20839/) (2026)

## Abstract (arXiv)

We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens in arbitrary order. While an ideal conditional predictor would be invariant to this order, practical dLLMs exhibit strong sensitivity to the unmasking order, creating a new channel for watermarking. dgMARK steers the unmasking order toward positions whose high-reward candidate tokens satisfy a simple parity constraint induced by a binary hash, without explicitly reweighting the model's learned probabilities. The method is plug-and-play with common decoding strategies (e.g., confidence, entropy, and margin-based ordering) and can be strengthened with a one-step lookahead variant. Watermarks are detected via elevated parity-matching statistics, and a sliding-window detector ensures robustness under post-editing operations including insertion, deletion, substitution, and paraphrasing. Project website: https://dgmark-watermarking.github.io