English
Related papers

Related papers: Can we Watermark Low-Entropy LLM Outputs?

200 papers

Large Language Model (LLM) watermarking is crucial for establishing the provenance of machine-generated text, but most existing methods rely on a centralized trust model. This model forces users to reveal potentially sensitive text to a…

Cryptography and Security · Computer Science 2026-05-01 Xiaokun Luan , Yihao Zhang , Pengcheng Su , Feiran Lei , Meng Sun

The advancements in audio generative models have opened up new challenges in their responsible disclosure and the detection of their misuse. In response, we introduce a method to watermark latent generative models by a specific watermarking…

Sound · Computer Science 2024-09-05 Robin San Roman , Pierre Fernandez , Antoine Deleforge , Yossi Adi , Romain Serizel

Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM rewrites existing text while applying generation-time watermarking, to protect…

Large language models (LLMs) are widely deployed in multiple scenarios due to reasoning capabilities. In order to prevent the models from being misused, watermarking is generally employed to ensure ownership. However, most existing…

Cryptography and Security · Computer Science 2026-04-29 Ziming Zhang , Li Li , Guorui Feng , Hanzhou Wu , Xinpeng Zhang

Text watermarking technology aims to tag and identify content produced by large language models (LLMs) to prevent misuse. In this study, we introduce the concept of cross-lingual consistency in text watermarking, which assesses the ability…

Computation and Language · Computer Science 2024-06-05 Zhiwei He , Binglin Zhou , Hongkun Hao , Aiwei Liu , Xing Wang , Zhaopeng Tu , Zhuosheng Zhang , Rui Wang

Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained on a test set. We introduce a solution to this problem by…

Cryptography and Security · Computer Science 2025-07-22 Tom Sander , Pierre Fernandez , Saeed Mahloujifar , Alain Durmus , Chuan Guo

The rapid growth of Large Language Models (LLMs) raises concerns about distinguishing AI-generated text from human content. Existing watermarking techniques, like \kgw, struggle with low watermark strength and stringent false-positive…

Machine Learning · Computer Science 2025-05-22 Zhuang Li , Qiuping Yi , Zongcheng Ji , Yijian Lu , Yanqi Li , Keyang Xiao , Hongliang Liang

Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property…

Machine Learning · Computer Science 2025-05-29 Hanlin Zhang , Benjamin L. Edelman , Danilo Francati , Daniele Venturi , Giuseppe Ateniese , Boaz Barak

Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive…

In the era of costly pre-training of large language models, ensuring the intellectual property rights of model owners, and insuring that said models are responsibly deployed, is becoming increasingly important. To this end, we propose model…

Computation and Language · Computer Science 2024-12-18 Vaden Masrani , Mohammad Akbari , David Ming Xuan Yue , Ahmad Rezaei , Yong Zhang

Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing control over data when it is being used to train such machine learning models or when distinguishing…

Cryptography and Security · Computer Science 2025-12-16 Malte Hellmeier

Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fully watermarked text from non-watermarked text, overlooking…

Computation and Language · Computer Science 2025-02-25 Leyi Pan , Aiwei Liu , Yijian Lu , Zitian Gao , Yichen Di , Shiyu Huang , Lijie Wen , Irwin King , Philip S. Yu

Large Language Models (LLMs) have demonstrated impressive capabilities in generating diverse and contextually rich text. However, concerns regarding copyright infringement arise as LLMs may inadvertently produce copyrighted material. In…

Large language models (LLMs) are increasingly integrated into academic workflows, with many conferences and journals permitting their use for tasks such as language refinement and literature summarization. However, their use in peer review…

Cryptography and Security · Computer Science 2025-11-13 Alexander Nemecek , Yuzhou Jiang , Erman Ayday

Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific downstream datasets, which makes it hard to claim the…

Computation and Language · Computer Science 2023-02-13 Chenxi Gu , Chengsong Huang , Xiaoqing Zheng , Kai-Wei Chang , Cho-Jui Hsieh

Various watermarking methods (``watermarkers'') have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations…

Cryptography and Security · Computer Science 2025-10-01 Jiacheng Liang , Zian Wang , Lauren Hong , Shouling Ji , Ting Wang

Digital watermarking is a promising solution for mitigating some of the risks arising from the misuse of automatically generated text. These approaches either embed non-specific watermarks to allow for the detection of any text generated by…

Cryptography and Security · Computer Science 2025-06-23 Zihao Fu , Chris Russell

We study watermarking schemes for language models with provable guarantees. As we show, prior works offer no robustness guarantees against adaptive prompting: when a user queries a language model more than once, as even benign users do. And…

Cryptography and Security · Computer Science 2024-07-02 Aloni Cohen , Alexander Hoover , Gabe Schoenbach

Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on $\emph{monitoring}$ to detect and flag unsafe behavior during inference. An open…

Cryptography and Security · Computer Science 2026-04-01 Toluwani Aremu , Daniil Ognev , Samuele Poppi , Nils Lukas

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.…

Cryptography and Security · Computer Science 2025-02-11 Ruisi Zhang , Neusha Javidnia , Nojan Sheybani , Farinaz Koushanfar