中文
相关论文

相关论文: Watermarking Conditional Text Generation for AI De…

200 篇论文

Potential harms of Large Language Models such as mass misinformation and plagiarism can be partially mitigated if there exists a reliable way to detect machine generated text. In this paper, we propose a new watermarking method to detect…

计算与语言 · 计算机科学 2023-12-12 Kaan Efe Keleş , Ömer Kaan Gürbüz , Mucahid Kutlu

Watermarking embeds information into digital content like images, audio, or text, imperceptible to humans but robustly detectable by specific algorithms. This technology has important applications in many challenges of the industry such as…

密码学与安全 · 计算机科学 2025-02-11 Pierre Fernandez

The rapid advancement of generative artificial intelligence (GenAI) has revolutionized content creation across text, visual, and audio domains, simultaneously introducing significant risks such as misinformation, identity fraud, and content…

密码学与安全 · 计算机科学 2025-04-08 Lele Cao

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

The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking…

密码学与安全 · 计算机科学 2026-04-16 Alexander Nemecek , Yuzhou Jiang , Erman Ayday

LLMs now exhibit human-like skills in various fields, leading to worries about misuse. Thus, detecting generated text is crucial. However, passive detection methods are stuck in domain specificity and limited adversarial robustness. To…

计算与语言 · 计算机科学 2023-05-17 Xi Yang , Kejiang Chen , Weiming Zhang , Chang Liu , Yuang Qi , Jie Zhang , Han Fang , Nenghai Yu

A generative AI model can generate extremely realistic-looking content, posing growing challenges to the authenticity of information. To address the challenges, watermark has been leveraged to detect AI-generated content. Specifically, a…

机器学习 · 计算机科学 2023-11-09 Zhengyuan Jiang , Jinghuai Zhang , Neil Zhenqiang Gong

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

机器学习 · 计算机科学 2024-05-03 John Kirchenbauer , Jonas Geiping , Yuxin Wen , Jonathan Katz , Ian Miers , Tom Goldstein

Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the…

计算与语言 · 计算机科学 2024-02-27 Massieh Kordi Boroujeny , Ya Jiang , Kai Zeng , Brian Mark

Recent advancements in watermarking techniques have enabled the embedding of secret messages into AI-generated text (AIGT), serving as an important mechanism for AIGT detection. Existing methods typically interfere with the generation…

密码学与安全 · 计算机科学 2025-06-10 Peiru Yang , Xintian Li , Wanchun Ni , Jinhua Yin , Huili Wang , Guoshun Nan , Shangguang Wang , Yongfeng Huang , Tao Qi

Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts. Watermarking is pivotal in this context, which involves…

机器学习 · 计算机科学 2024-06-07 Mingjia Huo , Sai Ashish Somayajula , Youwei Liang , Ruisi Zhang , Farinaz Koushanfar , Pengtao Xie

The task of discerning between generated and natural texts is increasingly challenging. In this context, watermarking emerges as a promising technique for ascribing generated text to a specific model. It alters the sampling generation…

计算与语言 · 计算机科学 2023-11-09 Pierre Fernandez , Antoine Chaffin , Karim Tit , Vivien Chappelier , Teddy Furon

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…

计算与语言 · 计算机科学 2023-10-16 Xuandong Zhao , Prabhanjan Ananth , Lei Li , Yu-Xiang Wang

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

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

Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in model outputs, by…

密码学与安全 · 计算机科学 2023-06-16 Miranda Christ , Sam Gunn , Or Zamir

As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical…

计算与语言 · 计算机科学 2025-08-07 Ruibo Chen , Yihan Wu , Junfeng Guo , Heng Huang

As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are a promising approach to address the problem of…

Watermarking generative-AI systems, such as LLMs, has gained considerable interest, driven by their enhanced capabilities across a wide range of tasks. Although current approaches have demonstrated that small, context-dependent shifts in…

计算与语言 · 计算机科学 2024-03-29 Piotr Molenda , Adian Liusie , Mark J. F. Gales

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…

机器学习 · 计算机科学 2025-05-22 Zhuang Li , Qiuping Yi , Zongcheng Ji , Yijian Lu , Yanqi Li , Keyang Xiao , Hongliang Liang
‹ 上一页 1 2 3 10 下一页 ›