Skip to content
Preprint

DHMark: Public-Key Watermarking for LLM-Generated Text via Diffie-Hellman-Guided Rejection Sampling

Aug 2026 · 0 citations · 37 references
Computer Science

TL;DR

DHMark is introduced, a public-key watermarking framework for LLM-generated text that avoids exact recovery of a long embedded signature and instead treats watermark detection as registry-aided statistical evidence aggregation.

Abstract

Large language model (LLM) watermarking provides an important mechanism for tracing the provenance of generated text. Existing statistical watermarks are often effective and robust, but most of them rely on private detection keys, which centralizes verification and complicates public auditing. Recent public or publicly verifiable watermarking schemes improve key management, yet many of them rely on exact recovery of embedded cryptographic strings, making them fragile under token edits, truncation, copy-paste, and low-entropy generation. This paper introduces DHMark, a public-key watermarking framework for LLM-generated text. The key idea is to separate payload authorization from noisy textual evidence. An issuer signs a short registry payload bound to a public context, and the payload is expanded into many one-bit equations. During generation, a Diffie-Hellman-guided token-labeling interface assigns each candidate token a public equation vote, and the sampler softly or selectively promotes candidates whose votes agree with the authorized payload. During verification, third-party verifiers use public information to extract token votes, aggregate them into equation-level evidence, and score only signed registry records. This design avoids exact recovery of a long embedded signature and instead treats watermark detection as registry-aided statistical evidence aggregation. We formalize the public-verification setting, analyze label pseudorandomness, registry-backed soundness, and sampling distortion, and evaluate a prototype under truncation, substitution, copy-paste, wrong-context, and plain-generation attacks. In the default 32-bit configuration, DHMark maintains at least a 0.967 valid rate across eight edit conditions while yielding a 0.000 acceptance rate on three negative controls.

View source

Similar papers

#machine learning Preprint Oct 2026

RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models

Large Language Model (LLM) watermarking provides a lightweight mechanism for identifying text generated by a specific model, but its robustness remains fragile under post-processing attacks. Deletion attacks are particularly challenging because they shift token positions and break the alignment between observed tokens...

Yi Wang, Bai-Cheng Chen, Yu Wang et al. · 0 citations

Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes

LLM watermarking has become an effective approach to distinguishing AI-generated text from human-written text by embedding detectable patterns during generation. However, a small post-generation edit may change the meaning of the text without removing its overall watermark signal, creating a risk that the modified cont...

Ze-Wei Deng, M. Siddeek, Li-Yan Xie et al. · 1 citation
#machine learning Preprint Oct 2026

Could LLM Watermark Detection be Public?

This work quantifies whether a public detector would be an additional liability in a deployment setting at varying levels of access, and introduces a split-key public-private watermarking method that exposes one key through a public detector while keeping the other for full verification and forensics.

Georgios Milis, Tom Sander, Tomás Soucek et al. · 0 citations
Preprint Aug 2026

WoE Wrote It? Watermarking Mixture-of-Experts LLMs for Black-Box Text Provenance

WoE remains detectable under adversarial supervised fine-tuning, model extraction, and output-level paraphrasing, forcing malicious actors into a trade-off in which weakening the attribution signal requires additional model adaptation or text-rewriting operations, or compromises the utility of the resulting output.

Jona te Lintelo, Li-Chao Wu, S. Picek · 0 citations
#artificial intelligence Preprint Oct 2026

Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents

Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks break in two ways. First, all three prior schemes bind the watermark to the exact action symbol, so renaming a tool desynchronizes decoding even when t...

Su-Xin Ji, Hung-Tao Wan, Shao-Xuan Chen et al. · 0 citations
#natural language process... Preprint Sep 2026

CertMark: Distortion-Free Multi-Bit Watermarking with Certified Decoding

Leading multi-bit watermarking methods for language models encode messages by biasing the model's next-token probabilities, creating a trade-off between message recovery and text quality. Their decoders typically return the highest-scoring candidate from accumulated token-level evidence, without a certified abstention...

Pawel Batorski, P. Spurek, Paul Swoboda · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.