DenMark: Robust Semantic Watermarking for Diffusion Language Models
cs.CL
Submitted: 2026-09-13
Updated: 2026-09-13
Code: https://github.com/PrithivirajDamodaran/Parrot_Paraphraser
License: http://creativecommons.org/licenses/by/4.0/
The gist: Semantic text watermarks encode signals in meaning rather than surface token choices, offering robustness to paraphrasing and other semantic-preserving edits.
Terminology
Abstract
Semantic text watermarks encode signals in meaning rather than surface token choices, offering robustness to paraphrasing and other semantic-preserving edits. Existing semantic watermarking methods are primarily designed for autoregressive language models (ARLMs), where completed candidate units can be generated and scored before generation proceeds. This paradigm does not naturally extend to diffusion language models (DLMs), where semantic units remain incomplete during intermediate denoising steps and tokens may be updated in flexible orders. We propose DenMark, a semantic watermarking framework that injects key-dependent signals directly into the DLM denoising process. DenMark partitions the output into fixed token regions and uses temporary rollouts as semantic lookahead: conditional completions estimate the eventual semantics of an incomplete region, enabling DenMark to select local updates with higher estimated semantic watermark scores. Repeating this procedure across denoising steps progressively accumulates watermark evidence in the final output. For detection, DenMark uses calibrated scanning over candidate unit sizes to remain robust to boundary shifts introduced by semantic attacks. Across four DLMs, three datasets, and four semantic attacks, DenMark achieves the best results across all reported detection metrics in all 48 backbone-dataset-attack combinations. These results demonstrate that DenMark provides an effective mechanism for robust semantic watermarking in DLMs.
Sources
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- On the Opportunities and Risks of Foundation Models
- Evaluating Large Language Models Trained on Code
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
- Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning
- LLaMA: Open and Efficient Foundation Language Models
- Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- Ethical and social risks of harm from Language Models
- Dream 7B: Diffusion Large Language Models
- LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering