CORE-BREW is a new multi‑bit watermarking method for large language models that uses log‑likelihood ratios for soft‑decision decoding, targeting a fixed hit rate to calibrate the watermark channel. It introduces entropy‑aware erasures to reduce perturbations in low‑entropy contexts and combines likelihood‑based scoring with soft‑decision list decoding to better exploit token‑level reliability. Experiments on open‑source LLMs show that CORE‑BREW improves detection robustness and payload recovery compared to the BREW baseline while keeping false‑positive rates low and maintaining translation quality metrics close to unwatermarked text.
By Joeun Kim, HoEun Kim, Young-Sik Kim
arXiv:2609.38722v1 Announce Type: cross
Abstract: LLM watermarking has become an effective approach to distinguishing AI-generated text from human-written text by embedding detectable patterns during...
By Zewei Deng, Muhammad Siddeek, Liyan Xie, Mohamed Seif, Mengdi Wang, H. Vincent Poor, Andrea Goldsmith
arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.
By Chih-Duo Hong, Yen-Pang Chen, Fang Yu
arXiv:2608.29575v1 Announce Type: new
Abstract: Large language models are increasingly used to read documents and produce downstream text, creating a provenance problem when the document owner cannot...
By Junyan Zhang, Yudong Zeng, Yongwei Huang, Zuhao Ouyang, Hong Chen, Xuming Hu
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
The paper introduces an adaptive embedding displacement attack (EDA) that exploits rewording, reordering, and resegmentation to remove semantic watermarks from text, achieving a 32.6%–47.9% success rate across four watermarking schemes. To counter this, the authors propose k‑SwordStamp, a semantic watermarking method that uses order‑robust detection over sub‑sentence units, significantly reducing vulnerability to structure‑based edits. Experiments show that EDA remains effective against k‑SwordStamp, but with a lower success rate (10.8%) compared to its performance on other schemes.
By Abdulrahman Diaa, Jonathan Petit, Florian Kerschbaum
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
AngelFingerprint introduces a watermarking framework for text-guided image editing that embeds the editing prompt’s CLIP text embedding directly into the diffusion model’s weights via a LoRA module. The watermark is recoverable from image pixels alone, providing an explainable trace of the edit while remaining stealthy even under full white-box access. Experiments on the MagicBrush dataset show the extractor achieves 86% top‑1 accuracy in 200‑way prompt retrieval, outperforming prompt inversion methods.
By Bo-Han Kung, Futa Waseda, Ching-Chun Chang, Isao Echizen, Shang-Tse Chen
arXiv:2608. 19727v1 Announce Type: cross Abstract: Watermarking is a central tool for provenance in generative models, yet its application to multivariate time series remains hindered by reliability failures under post-editing attacks.
By Dongbin Kim, Geonwoo Shin, Yujin Choi, Soyeon Park, Jaewook Lee
arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.
By Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas
arXiv:2503.04332v2 Announce Type: replace-cross
Abstract: The tremendous commercial potential of large language models (LLMs) has heightened concerns over their unauthorized use. To address this, we...
By Ziqing Yang, Yixin Wu, Yun Shen, Wei Dai, Michael Backes, Yang Zhang
arXiv:2607. 20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly into their weights.
By Luisa Scharff, Thibaud Gloaguen, Robin Staab, Martin Vechev