From TDMA to CDMA: A Multi-bit Watermark for Diffusion Language Models

ACL ARR 2026 January Submission10130 Authors

Keywords: Watermark, LLM, Diffusion Language Model

Abstract:

While DLMs have emerged as an alternative to ARMs, robust content provenance mechanisms for this architecture remain unexplored. Existing multi-bit watermarking schemes, heavily reliant on the sequential context of ARMs, cannot be directly applied to DLMs. In this paper, we reframe the multi-bit watermarking problem through a novel Digital Signal Processing (DSP) lens. We draw an analogy between prior works and TDMA (Time Division Multiple Access) in telecommunications, revealing their inherent limitations.
To overcome these limitations, we introduce \textbf{CDMArk}, the first multi-bit watermarking framework tailored for DLMs, orchestrating a paradigm shift from TDMA to CDMA (Code Division Multiple Access). Our method encodes the entire watermark message across all tokens holographically. We further provide rigorous statistical guarantees for the watermark detection process. Extensive experiments demonstrate that CDMArk achieves a new state-of-the-art Pareto frontier between imperceptibility and effectiveness.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: security/privacy

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 10130