Watermarking Discrete Diffusion Language Models

Avi Bagchi, Akhil Bhimaraju, Moulik Choraria, Daniel Alabi, Lav R. Varshney

Keywords: watermarking, discrete diffusion

TL;DR: A watermark for discrete diffusion models.

Abstract: 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 the 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 preserves the marginal token distribution at each diffusion step, 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.

Submission Number: 191