Score: 1

Watermarking Discrete Diffusion Language Models

Published: November 3, 2025 | arXiv ID: 2511.02083v1

By: Avi Bagchi , Akhil Bhimaraju , Moulik Choraria and more

Potential Business Impact:

Marks AI writing so you know it's fake.

Business Areas:
DRM Content and Publishing, Media and Entertainment, Privacy and Security

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, none address discrete diffusion language models, which are becoming popular due to their high inference throughput. In this paper, we introduce the first watermarking method for discrete diffusion models by applying the distribution-preserving Gumbel-max trick at every diffusion step and seeding the randomness with the sequence index to enable reliable detection. We experimentally demonstrate that our scheme is reliably detectable on state-of-the-art diffusion language models and analytically prove that it is distortion-free with an exponentially decaying probability of false detection in the token sequence length.

Repos / Data Links

Page Count
13 pages

Category
Computer Science:
Cryptography and Security