English
Related papers

Related papers: Undetectable Watermarks for Language Models

200 papers

To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection.…

Computation and Language · Computer Science 2024-02-14 Yu Fu , Deyi Xiong , Yue Dong

Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated content is a response to a fabricated prompt. None of them can be…

Cryptography and Security · Computer Science 2024-12-30 Minhao Bai

Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's next-token probability distribution, which is typically not…

Cryptography and Security · Computer Science 2026-02-24 Dara Bahri , John Wieting

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…

Cryptography and Security · Computer Science 2025-02-11 Pierre Fernandez

In the rapidly evolving domain of artificial intelligence, safeguarding the intellectual property of Large Language Models (LLMs) is increasingly crucial. Current watermarking techniques against model extraction attacks, which rely on…

Cryptography and Security · Computer Science 2024-05-03 Minhao Bai , Kaiyi Pang , Yongfeng Huang

Embedding watermarks into the output of generative models is essential for establishing copyright and verifiable ownership over the generated content. Emerging diffusion model watermarking methods either embed watermarks in the frequency…

Image and Video Processing · Electrical Eng. & Systems 2025-02-18 Yunzhuo Chen , Jordan Vice , Naveed Akhtar , Nur Al Hasan Haldar , Ajmal Mian

We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many adaptive queries.…

Cryptography and Security · Computer Science 2025-04-23 Sam Gunn , Xuandong Zhao , Dawn Song

Recently, text watermarking algorithms for large language models (LLMs) have been proposed to mitigate the potential harms of text generated by LLMs, including fake news and copyright issues. However, current watermark detection algorithms…

Computation and Language · Computer Science 2024-05-28 Aiwei Liu , Leyi Pan , Xuming Hu , Shu'ang Li , Lijie Wen , Irwin King , Philip S. Yu

The effectiveness of watermark algorithms in AI-generated text identification has garnered significant attention. Concurrently, an increasing number of watermark algorithms have been proposed to enhance the robustness against various…

Cryptography and Security · Computer Science 2024-10-01 Xianheng Feng , Jian Liu , Kui Ren , Chun Chen

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…

Cryptography and Security · Computer Science 2025-01-27 Adam Block , Ayush Sekhari , Alexander Rakhlin

Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a secret watermark key. A core security threat are forgery…

Cryptography and Security · Computer Science 2026-05-12 Toluwani Aremu , Noor Hussein , Munachiso Nwadike , Samuele Poppi , Jie Zhang , Karthik Nandakumar , Neil Gong , Nils Lukas

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…

Cryptography and Security · Computer Science 2026-04-15 Noam Mazor , Andrew Morgan , Rafael Pass

The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible…

Cryptography and Security · Computer Science 2025-11-04 Shingo Kodama , Haya Diwan , Lucas Rosenblatt , R. Teal Witter , Niv Cohen

In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are…

Cryptography and Security · Computer Science 2025-06-13 Shayleen Reynolds , Hengzhi He , Dung Daniel T. Ngo , Saheed Obitayo , Niccolò Dalmasso , Guang Cheng , Vamsi K. Potluru , Manuela Veloso

Given a text, can we determine whether it was generated by a large language model (LLM) or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking scheme in the closed…

Cryptography and Security · Computer Science 2025-06-26 Pedro Abdalla , Roman Vershynin

Watermarking for large language models (LLMs) offers a promising approach to identifying AI-generated text. Existing approaches, however, either compromise the distribution of original generated text by LLMs or are limited to embedding…

Cryptography and Security · Computer Science 2025-06-09 Ya Jiang , Chuxiong Wu , Massieh Kordi Boroujeny , Brian Mark , Kai Zeng

Generative models that can produce realistic images have improved significantly in recent years. The quality of the generated content has increased drastically, so sometimes it is very difficult to distinguish between the real images and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Mikhail Pautov , Danil Ivanov , Andrey V. Galichin , Oleg Rogov , Ivan Oseledets

The indistinguishability of AI-generated content from human text raises challenges in transparency and accountability. While several methods exist to watermark models behind APIs, embedding watermark strategies directly into model weights…

Machine Learning · Computer Science 2025-04-10 Fay Elhassan , Niccolò Ajroldi , Antonio Orvieto , Jonas Geiping

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…

Computation and Language · Computer Science 2023-11-09 Pierre Fernandez , Antoine Chaffin , Karim Tit , Vivien Chappelier , Teddy Furon

Existing watermarking methods for large language models (LLMs) mainly embed watermark by adjusting the token sampling prediction or post-processing, lacking intrinsic coupling with LLMs, which may significantly reduce the semantic quality…

Cryptography and Security · Computer Science 2025-10-17 Siyuan Bao , Ying Shi , Zhiguang Yang , Hanzhou Wu , Xinpeng Zhang