中文
相关论文

相关论文: Covert Multi-bit LLM Watermarking: An Information …

200 篇论文

Training data is a critical and often proprietary asset in Large Language Model (LLM) development, motivating the use of data watermarking to embed model-transferable signals for usage verification. We identify low coverage as a vital yet…

密码学与安全 · 计算机科学 2026-04-30 Hengyu Wu , Yang Cao

Amidst rising concerns about the internet being proliferated with content generated from language models (LMs), watermarking is seen as a principled way to certify whether text was generated from a model. Many recent watermarking techniques…

密码学与安全 · 计算机科学 2024-11-11 Saksham Rastogi , Danish Pruthi

Large Language Models (LLMs) excel in various applications, including text generation and complex tasks. However, the misuse of LLMs raises concerns about the authenticity and ethical implications of the content they produce, such as…

密码学与安全 · 计算机科学 2024-12-02 Zesen Liu , Tianshuo Cong , Xinlei He , Qi Li

Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construct a green/red token list and assign higher or lower…

密码学与安全 · 计算机科学 2025-10-27 Li An , Yujian Liu , Yepeng Liu , Yuheng Bu , Yang Zhang , Shiyu Chang

Recent advancements in large language models (LLMs) have highlighted the risk of misusing them, raising the need for accurate detection of LLM-generated content. In response, a viable solution is to inject imperceptible identifiers into…

计算与语言 · 计算机科学 2025-02-11 Minjia Mao , Dongjun Wei , Zeyu Chen , Xiao Fang , Michael Chau

As open-source large language models (LLMs) like Llama3 become more capable, it is crucial to develop watermarking techniques to detect their potential misuse. Existing watermarking methods either add watermarks during LLM inference, which…

计算与语言 · 计算机科学 2025-03-18 Yijie Xu , Aiwei Liu , Xuming Hu , Lijie Wen , Hui Xiong

The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring…

计算与语言 · 计算机科学 2025-09-12 Amirhossein Dabiriaghdam , Lele Wang

Recent advances in large language models have raised wide concern in generating abundant plausible source code without scrutiny, and thus tracing the provenance of code emerges as a critical issue. To solve the issue, we propose CodeMark, a…

密码学与安全 · 计算机科学 2023-05-23 Wei Li , Borui Yang , Yujie Sun , Suyu Chen , Ziyun Song , Liyao Xiang , Xinbing Wang , Chenghu Zhou

Recent progress in large language models enables the creation of realistic machine-generated content. Watermarking is a promising approach to distinguish machine-generated text from human text, embedding statistical signals in the output…

密码学与安全 · 计算机科学 2026-02-25 Patrick Chao , Yan Sun , Edgar Dobriban , Hamed Hassani

With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code LM…

编程语言 · 计算机科学 2025-09-18 Boyu Zhang , Ping He , Tianyu Du , Xuhong Zhang , Lei Yun , Kingsum Chow , Jianwei Yin

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…

密码学与安全 · 计算机科学 2025-11-17 Yanbo Dai , Zongjie Li , Zhenlan Ji , Shuai Wang

The development of large language models (LLMs) has raised concerns about potential misuse. One practical solution is to embed a watermark in the text, allowing ownership verification through watermark extraction. Existing methods primarily…

密码学与安全 · 计算机科学 2025-03-04 Yuhang Cai , Yaofei Wang , Donghui Hu , Chen Gu

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

机器学习 · 统计学 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a…

密码学与安全 · 计算机科学 2026-02-24 Hyeseon An , Shinwoo Park , Suyeon Woo , Yo-Sub Han

As large language models become standard backends for content generation, practical provenance increasingly requires multi-bit watermarking. In provider-internal deployments, a key requirement is message symmetry: the message itself should…

计算与语言 · 计算机科学 2026-04-16 Junlin Zhu , Baizhou Huang , Xiaojun Wan

A recent and exciting thread of work focuses on developing methods for watermarking the output of large language models (LLMs). We focus on provably undetectable watermarking-that is, schemes that do not alter the output distribution of the…

密码学与安全 · 计算机科学 2026-04-15 Noam Mazor , Andrew Morgan , Rafael Pass

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…

密码学与安全 · 计算机科学 2025-10-06 Yu Zhang , Shuliang Liu , Xu Yang , Xuming Hu

The proliferation of open-source code and large language models (LLMs) for code generation has amplified the risks of unauthorized reuse and intellectual property infringement. Source code watermarking offers a potential solution, yet…

密码学与安全 · 计算机科学 2026-04-21 Rui Xu , Jiawei Chen , Weizhi Liu , Zhaoxia Yin , Cong Kong , Xinpeng Zhang

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…

密码学与安全 · 计算机科学 2024-05-24 Baizhou Huang , Xiaojun Wan

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…

密码学与安全 · 计算机科学 2024-10-25 Miranda Christ , Sam Gunn , Tal Malkin , Mariana Raykova