English
Related papers

Related papers: Invisible Entropy: Towards Safe and Efficient Low-…

200 papers

We study the problem of watermarking large language models (LLMs) generated text -- one of the most promising approaches for addressing the safety challenges of LLM usage. In this paper, we propose a rigorous theoretical framework to…

Computation and Language · Computer Science 2023-10-16 Xuandong Zhao , Prabhanjan Ananth , Lei Li , Yu-Xiang Wang

In large language models (LLMs), each block operates on the residual stream to map input token sequences to output token distributions. However, most of the interpretability literature focuses on internal latent representations, leaving…

Machine Learning · Computer Science 2026-02-03 Riccardo Ali , Francesco Caso , Christopher Irwin , Pietro Liò

Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking, has been used as a principled approach to provable detection…

Statistics Theory · Mathematics 2025-08-28 Xiang Li , Feng Ruan , Huiyuan Wang , Qi Long , Weijie J. Su

This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information…

Cryptography and Security · Computer Science 2025-07-03 Haiyun He , Yepeng Liu , Ziqiao Wang , Yongyi Mao , Yuheng Bu

The rise of Large Language Models (LLMs) has heightened concerns about the misuse of AI-generated text, making watermarking a promising solution. Mainstream watermarking schemes for LLMs fall into two categories: logits-based and…

Computation and Language · Computer Science 2025-05-19 Yidan Wang , Yubing Ren , Yanan Cao , Binxing Fang

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

The rise of LLMs has increased concerns over source tracing and copyright protection for AIGC, highlighting the need for advanced detection technologies. Passive detection methods usually face high false positives, while active watermarking…

Cryptography and Security · Computer Science 2026-04-03 Kahim Wong , Jicheng Zhou , Jiantao Zhou , Yain-Whar Si

Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises…

Cryptography and Security · Computer Science 2025-01-29 Wenjie Qu , Wengrui Zheng , Tianyang Tao , Dong Yin , Yanze Jiang , Zhihua Tian , Wei Zou , Jinyuan Jia , Jiaheng Zhang

The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…

Cryptography and Security · Computer Science 2024-10-25 Miranda Christ , Sam Gunn , Tal Malkin , Mariana Raykova

Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of watermarking schemes, several of which focus on preserving…

Cryptography and Security · Computer Science 2025-02-25 Thibaud Gloaguen , Nikola Jovanović , Robin Staab , Martin Vechev

Watermarking large language models (LLMs) is vital for preventing their misuse, including the fabrication of fake news, plagiarism, and spam. It is especially important to watermark LLM-generated code, as it often contains intellectual…

Cryptography and Security · Computer Science 2025-12-18 Li Lin , Siyuan Xin , Yang Cao , Xiaochun Cao

With the increasing use of large language models (LLMs) in daily life, concerns have emerged regarding their potential misuse and societal impact. Watermarking is proposed to trace the usage of specific models by injecting patterns into…

Cryptography and Security · Computer Science 2024-05-24 Baizhou Huang , Xiaojun Wan

With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text.…

Cryptography and Security · Computer Science 2024-07-22 Duy C. Hoang , Hung T. Q. Le , Rui Chu , Ping Li , Weijie Zhao , Yingjie Lao , Khoa D. Doan

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

Computation and Language · Computer Science 2026-05-29 Yukang Lin , Jiahao Shao , Shuoran Jiang , Wentao Zhu , Bingjie Lu , Xiangping Wu , Joanna Siebert , Qingcai Chen

As large language models (LLMs) reach human-like fluency, reliably distinguishing AI-generated text from human authorship becomes increasingly difficult. While watermarks already exist for LLMs, they often lack flexibility and struggle with…

Computation and Language · Computer Science 2025-06-18 Georg Niess , Roman Kern

LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of…

Cryptography and Security · Computer Science 2024-10-29 Leyi Pan , Aiwei Liu , Zhiwei He , Zitian Gao , Xuandong Zhao , Yijian Lu , Binglin Zhou , Shuliang Liu , Xuming Hu , Lijie Wen , Irwin King , Philip S. Yu

LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up…

Cryptography and Security · Computer Science 2026-02-09 Thibaud Gloaguen , Robin Staab , Nikola Jovanović , Martin Vechev

Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially…

Cryptography and Security · Computer Science 2025-10-06 Yu Zhang , Shuliang Liu , Xu Yang , Xuming Hu

While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific detectors for verification. This dependency…

Cryptography and Security · Computer Science 2026-04-14 Zhuoshang Wang , Yubing Ren , Yanan Cao , Fang Fang , Xiaoxue Li , Li Guo

The Large Language Model (LLM) watermark is a newly emerging technique that shows promise in addressing concerns surrounding LLM copyright, monitoring AI-generated text, and preventing its misuse. The LLM watermark scheme commonly includes…

Cryptography and Security · Computer Science 2024-05-31 Zhaoxi Zhang , Xiaomei Zhang , Yanjun Zhang , Leo Yu Zhang , Chao Chen , Shengshan Hu , Asif Gill , Shirui Pan