← Back to all news
arXiv Computation and Language By Jonas Sch\"afer, Cezary Pilaszewicz, Gerhard Wunder

Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings

Read the original on arXiv Computation and Language →

The paper introduces Dual-Embedding Watermarking (DEW), a semantic watermarking technique for large language models that combines contextual and token-level embeddings. DEW applies algebraic vector-space operations to generate a watermark signal that remains robust to paraphrasing and translation, while obfuscating the signal with pseudo-random matrices seeded by a secret key. Experiments demonstrate state‑of‑the‑art robustness, especially against translation, with minimal computational overhead and preserved text quality at lower watermark strengths.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Sep 30

TTMark: Pairwise Distortion-Free Watermarking Beyond Single-Token Entropy

TTMark introduces a pairwise watermarking framework that extends distortion‑free watermarking from single tokens to adjacent token pairs, enlarging the watermarking alphabet from V to V². By watermarking the joint distribution of consecutive tokens, the detector can exploit both token entropy and conditional entropy while maintaining distortion‑freeness. Experiments on multiple language models and datasets show that TTMARK improves detectability, robustness to edits, and localized watermark detection without degrading generation quality.

By Ruibo Chen, Zhengmian Hu, Donghang Lu, Xuehao Cui, Georgios Milis, Yihan Wu, Jian Du, Heng Huang
llms
More like this →
arXiv Machine Learning
Sep 30

Dataset Watermarking with Provable Black-Box Detection

The paper introduces a dataset watermarking technique that embeds a watermark by increasing the co‑occurrence of randomly selected word pairs through meaning‑preserving local edits. The watermark can be detected solely from generated text with provable false‑positive control, and experiments on four base models and three datasets show reliable detection (p < 0.01) even when the watermarked data constitutes less than 5% of fine‑tuning tokens. Compared to existing methods, the approach better preserves benchmark utility and semantic integrity.

By Pengrun Huang, Kamalika Chaudhuri, Yu-Xiang Wang
llmsfine-tuningbenchmarks
More like this →