Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings

Abstract:This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large language models (LLMs) that leverages contextual and token-level embeddings to enhance robustness against paraphrasing and translation. DEW utilizes a signal-processing methodology, applying algebraic vector-space operations to token and context embeddings to derive a watermark signal that degrades gracefully under semantic shifts. The method obfuscates the watermark by projecting embedding vectors through pseudo-random matrices seeded with a secret key. Experimental results show that dual-embedding watermarking can offer state-of-the-art robustness, particularly against translation, while incurring relatively low computational overhead compared with other semantic schemes. At lower watermark strength, DEW also maintains competitive text quality, suggesting that dual-embedding signals provide a promising substrate for robust semantic watermarking.

Accepted to Findings of EMNLP 2026. 22 pages, 10 tables, 1 figure

Computation and Language (cs.CL); Cryptography and Security (cs.CR)

arXiv:2606.31602 [cs.CL]

(or arXiv:2606.31602v3 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.31602 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.