WeaveMark is a new multi‑bit watermarking scheme for large language models that improves payload capacity, extraction accuracy, and text quality by using coded payload spreading, soft‑decision error‑correcting codes, and unbiased multilayer reweighting. It also adds zero‑bit layers for reliable detection of watermark presence. Experiments demonstrate significant gains, achieving an 89.8% match rate for 32‑bit messages at 200 tokens and maintaining 86.0% accuracy under 10% substitution attacks on 16‑bit messages, far outperforming the BiMark baseline.
By Gang-Hyun Park, Ju-Hyeong Lee, Hee-Youl Kwak, Dae-Young Yun
arXiv:2608.27899v1 Announce Type: cross
Abstract: With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to...
By Miroojin Bakshi, Saksham Rastogi, Danish Pruthi
arXiv:2512. 13325v2 Announce Type: replace-cross Abstract: Securing digital text is becoming increasingly relevant due to the widespread use of large language models.
By Malte Hellmeier
arXiv:2502.10673v2 Announce Type: replace-cross
Abstract: Retrieval-Augmented Generation (RAG) has become an effective method for enhancing large language models (LLMs) with up-to-date knowledge. How...
By Yepeng Liu, Xuandong Zhao, Dawn Song, Yuheng Bu
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.
By Jonas Sch\"afer, Cezary Pilaszewicz, Gerhard Wunder
arXiv:2604. 20269v2 Announce Type: replace-cross Abstract: With the popularity of the large language models (LLMs), text steganography has achieved remarkable performance.
By Jianxin Gao, Ruohan Lei, Wanli Peng
arXiv:2607. 06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need.
By Soohyeon Choi, Debin Gao, Yue Duan
arXiv:2502. 02068v3 Announce Type: replace-cross Abstract: This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property rights violations and inappropriate misuse in software development.
By Ruisi Zhang, Neusha Javidnia, Nojan Sheybani, Farinaz Koushanfar
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
arXiv:2609.06708v1 Announce Type: cross
Abstract: Large language models are transforming many industries with their text generation abilities. However, their outputs can be easily tampered with, crea...
By Zhongli Fang, Yiran Chen, Lingyun Zhang, Yu Liu, Ping Chen, Xiaoyan Sun, Jun Dai
arXiv:2606. 17123v1 Announce Type: cross Abstract: In open large language model (LLM) ecosystems, models are frequently adapted across multiple domains and applications, forming multi-stage derivation chains.
By Bingxue Zhang, Xiaofeng Xu, Feida Zhu
The paper demonstrates that N‑gram based code watermarking schemes, widely used to identify machine‑generated code, are ineffective when faced with realistic code obfuscation. By modeling semantics‑preserving transformations as a Markov random walk and introducing the assumption of distribution consistency, the authors prove that obfuscation can drive the failure rate of any detector to nearly 1 minus its false‑positive rate. Extensive experiments across multiple watermarking methods, LLMs, languages, benchmarks, and obfuscators confirm that detectors collapse to near‑random performance (AUROC ≈ 0.5) after obfuscation.
By Gehao Zhang, Mingzhe Li, Eugene Bagdasarian, Shiqing Ma, Juan Zhai