中文
相关论文

相关论文: Robust Distortion-free Watermarks for Language Mod…

200 篇论文

Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…

计算机视觉与模式识别 · 计算机科学 2025-02-11 Zhongjie Ba , Yitao Zhang , Peng Cheng , Bin Gong , Xinyu Zhang , Qinglong Wang , Kui Ren

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…

密码学与安全 · 计算机科学 2024-05-31 Zhaoxi Zhang , Xiaomei Zhang , Yanjun Zhang , Leo Yu Zhang , Chao Chen , Shengshan Hu , Asif Gill , Shirui Pan

Recent advances in Large Language Models (LLMs) have raised urgent concerns about LLM-generated text authenticity, prompting regulatory demands for reliable identification mechanisms. Although watermarking offers a promising solution,…

计算与语言 · 计算机科学 2025-08-26 Xiaoyan Feng , He Zhang , Yanjun Zhang , Leo Yu Zhang , Shirui Pan

Watermarking the outputs of large language models (LLMs) is critical for provenance tracing, content regulation, and model accountability. Existing approaches often rely on access to model internals or are constrained by static rules and…

机器学习 · 计算机科学 2025-06-23 Agnibh Dasgupta , Abdullah Tanvir , Xin Zhong

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…

密码学与安全 · 计算机科学 2025-09-16 Zhaoxi Zhang , Xiaomei Zhang , Yanjun Zhang , He Zhang , Shirui Pan , Bo Liu , Asif Qumer Gill , Leo Yu Zhang

Misuse of LLM-generated text can be curbed by watermarking techniques that embed implicit signals into the output. We propose a watermark that partitions the vocabulary at each decoding step into three sets (Green/Yellow/Red) with fixed…

计算与语言 · 计算机科学 2025-12-23 Zhiqing Hu , Chenxu Zhao , Jiazhong Lu , Xiaolei Liu

Language model (LM) watermarking techniques inject a statistical signal into LM-generated content by substituting the random sampling process with pseudo-random sampling, using watermark keys as the random seed. Among these statistical…

密码学与安全 · 计算机科学 2024-06-06 Yihan Wu , Ruibo Chen , Zhengmian Hu , Yanshuo Chen , Junfeng Guo , Hongyang Zhang , Heng Huang

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

Recent advances in Large Language Models (LLMs) have led to significant improvements in natural language processing tasks, but their ability to generate human-quality text raises significant ethical and operational concerns in settings…

密码学与安全 · 计算机科学 2025-01-27 Adam Block , Ayush Sekhari , Alexander Rakhlin

To mitigate the potential misuse of large language models (LLMs), recent research has developed watermarking algorithms, which restrict the generation process to leave an invisible trace for watermark detection. Due to the two-stage nature…

计算与语言 · 计算机科学 2024-07-02 Shangqing Tu , Yuliang Sun , Yushi Bai , Jifan Yu , Lei Hou , Juanzi Li

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…

计算与语言 · 计算机科学 2025-06-18 Georg Niess , Roman Kern

Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property. The literature has shown great interest in attacks on watermarking schemes: attackers are…

密码学与安全 · 计算机科学 2026-05-19 Maria Bulychev , Neil G. Marchant , Benjamin I. P. Rubinstein

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…

计算与语言 · 计算机科学 2024-12-18 Vaden Masrani , Mohammad Akbari , David Ming Xuan Yue , Ahmad Rezaei , Yong Zhang

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…

声音 · 计算机科学 2024-09-05 Robin San Roman , Pierre Fernandez , Antoine Deleforge , Yossi Adi , Romain Serizel

LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment. In this work we dispute this claim, identifying watermark…

机器学习 · 计算机科学 2024-06-25 Nikola Jovanović , Robin Staab , Martin Vechev

Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text…

密码学与安全 · 计算机科学 2024-10-21 Eva Giboulot , Teddy Furon

Detecting whether copyright holders' works were used in LLM pretraining is poised to be an important problem. This work proposes using data watermarks to enable principled detection with only black-box model access, provided that the…

密码学与安全 · 计算机科学 2024-08-20 Johnny Tian-Zheng Wei , Ryan Yixiang Wang , Robin Jia

Large language model (LLM) watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate by changing the next-token predictions output by an LLM. The…

In recent years, watermarking generative tabular data has become a prominent framework to protect against the misuse of synthetic data. However, while most prior work in watermarking methods for tabular data demonstrate a wide variety of…

The rise in malicious usage of large language models, such as fake content creation and academic plagiarism, has motivated the development of approaches that identify AI-generated text, including those based on watermarking or outlier…

计算与语言 · 计算机科学 2023-10-19 Kalpesh Krishna , Yixiao Song , Marzena Karpinska , John Wieting , Mohit Iyyer