English
Related papers

Related papers: Watermarking Language Models for Many Adaptive Use…

200 papers

Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns and has been widely deployed in industry. However,…

Cryptography and Security · Computer Science 2024-07-08 Zhengyuan Jiang , Moyang Guo , Yuepeng Hu , Jinyuan Jia , Neil Zhenqiang Gong

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…

Cryptography and Security · Computer Science 2024-12-02 Zesen Liu , Tianshuo Cong , Xinlei He , Qi Li

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…

Sound · Computer Science 2024-09-05 Robin San Roman , Pierre Fernandez , Antoine Deleforge , Yossi Adi , Romain Serizel

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…

Cryptography and Security · Computer Science 2025-03-04 Yuhang Cai , Yaofei Wang , Donghui Hu , Chen Gu

The rapid advancement of large language models (LLMs) has raised concerns regarding their potential misuse, particularly in generating fake news and misinformation. To address these risks, watermarking techniques for autoregressive language…

Cryptography and Security · Computer Science 2025-06-24 Koichi Nagatsuka , Terufumi Morishita , Yasuhiro Sogawa

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

Trigger set-based watermarking schemes have gained emerging attention as they provide a means to prove ownership for deep neural network model owners. In this paper, we argue that state-of-the-art trigger set-based watermarking algorithms…

Cryptography and Security · Computer Science 2023-01-20 Suyoung Lee , Wonho Song , Suman Jana , Meeyoung Cha , Sooel Son

As large language models become increasingly capable and widely deployed, verifying the provenance of machine-generated content is critical to ensuring trust, safety, and accountability. Watermarking techniques have emerged as a promising…

Cryptography and Security · Computer Science 2025-09-30 Yihan Wu , Ruibo Chen , Georgios Milis , Heng Huang

The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation. Audio watermarking offers a promising solution via embedding…

Machine Learning · Computer Science 2024-11-14 Hongbin Liu , Moyang Guo , Zhengyuan Jiang , Lun Wang , Neil Zhenqiang Gong

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

State-of-the-art text-to-image models generate photorealistic images at an unprecedented speed. This work focuses on models that operate in a bitwise autoregressive manner over a discrete set of tokens that is practically infinite in size.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Louis Kerner , Michel Meintz , Bihe Zhao , Franziska Boenisch , Adam Dziedzic

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Shilin Lu , Zihan Zhou , Jiayou Lu , Yuanzhi Zhu , Adams Wai-Kin Kong

We propose an imperceptible multi-bit text watermark embedded by paraphrasing with LLMs. We fine-tune a pair of LLM paraphrasers that are designed to behave differently so that their paraphrasing difference reflected in the text semantics…

Artificial Intelligence · Computer Science 2025-06-18 Xiaojun Xu , Jinghan Jia , Yuanshun Yao , Yang Liu , Hang Li

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…

Computation and Language · Computer Science 2023-05-17 Xi Yang , Kejiang Chen , Weiming Zhang , Chang Liu , Yuang Qi , Jie Zhang , Han Fang , Nenghai Yu

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

Machine Learning · Computer Science 2025-06-04 Tianci Liu , Tong Yang , Quan Zhang , Qi Lei

Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property…

Machine Learning · Computer Science 2025-05-29 Hanlin Zhang , Benjamin L. Edelman , Danilo Francati , Daniele Venturi , Giuseppe Ateniese , Boaz Barak

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and…

Computation and Language · Computer Science 2025-04-17 Shizhan Cai , Liang Ding , Dacheng Tao

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…

Computation and Language · Computer Science 2024-02-27 Massieh Kordi Boroujeny , Ya Jiang , Kai Zeng , Brian Mark

The rapid adoption of large language models (LLMs), such as GPT-4 and Claude 3.5, underscores the need to distinguish LLM-generated text from human-written content to mitigate the spread of misinformation and misuse in education. One…

Machine Learning · Statistics 2025-11-11 Xingchi Li , Xiaochi Liu , Guanxun Li

In recent years, various watermarking methods were suggested to detect computer vision models obtained illegitimately from their owners, however they fail to demonstrate satisfactory robustness against model extraction attacks. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Jacob Shams , Ben Nassi , Ikuya Morikawa , Toshiya Shimizu , Asaf Shabtai , Yuval Elovici