English
Related papers

Related papers: Beyond A Fixed Seal: Adaptive Stealing Watermark i…

200 papers

The growing use of large language models (LLMs) for sensitive applications has highlighted the need for effective watermarking techniques to ensure the provenance and accountability of AI-generated text. However, most existing watermarking…

Computation and Language · Computer Science 2026-04-07 Yepeng Liu , Xuandong Zhao , Christopher Kruegel , Dawn Song , Yuheng Bu

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

Various threats posed by the progress in text-to-speech (TTS) have prompted the need to reliably trace synthesized speech. However, contemporary approaches to this task involve adding watermarks to the audio separately after generation, a…

Sound · Computer Science 2024-11-18 Junzuo Zhou , Jiangyan Yi , Tao Wang , Jianhua Tao , Ye Bai , Chu Yuan Zhang , Yong Ren , Zhengqi Wen

Watermarking is a technical alternative to safeguarding intellectual property and reducing misuse. Existing methods focus on optimizing watermarked latent variables to balance watermark robustness and fidelity, as Latent diffusion models…

Image and Video Processing · Electrical Eng. & Systems 2026-02-09 Liangqi Lei , Keke Gai , Jing Yu , Qi Wu

A new local watermarking method based on histogram shifting has been proposed in this paper to deal with various signal processing attacks (e.g. median filtering, JPEG compression and Gaussian noise addition) and geometric attacks (e.g.…

Multimedia · Computer Science 2023-02-09 Zi-yu Jiang , Chi-Man Pun , Xiao-Chen Yuan , Tong Liu

Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, particularly, the API misuse and model extraction attacks. Various studies have…

Cryptography and Security · Computer Science 2025-02-18 Zekun Fei , Biao Yi , Jianing Geng , Ruiqi He , Lihai Nie , Zheli Liu

Text watermarking plays a crucial role in ensuring the traceability and accountability of large language model (LLM) outputs and mitigating misuse. While promising, most existing methods assume perfect pseudorandomness. In practice,…

Statistics Theory · Mathematics 2026-01-21 T. Tony Cai , Xiang Li , Qi Long , Weijie J. Su , Garrett G. Wen

Machine learning involves expensive data collection and training procedures. Model owners may be concerned that valuable intellectual property can be leaked if adversaries mount model extraction attacks. As it is difficult to defend against…

Cryptography and Security · Computer Science 2021-02-22 Hengrui Jia , Christopher A. Choquette-Choo , Varun Chandrasekaran , Nicolas Papernot

AI-generated text (AIGT) detection evasion aims to reduce the detection probability of AIGT, helping to identify weaknesses in detectors and enhance their effectiveness and reliability in practical applications. Although existing evasion…

Cryptography and Security · Computer Science 2025-08-25 Yinghan Zhou , Juan Wen , Wanli Peng , Zhengxian Wu , Ziwei Zhang , Yiming Xue

Machine learning (ML) models are applied in an increasing variety of domains. The availability of large amounts of data and computational resources encourages the development of ever more complex and valuable models. These models are…

Cryptography and Security · Computer Science 2021-12-09 Franziska Boenisch

In this paper, we initiate the study of \emph{multi-designated detector watermarking (MDDW)} for large language models (LLMs). This technique allows model providers to generate watermarked outputs from LLMs with two key properties: (i) only…

Cryptography and Security · Computer Science 2024-10-02 Zhengan Huang , Gongxian Zeng , Xin Mu , Yu Wang , Yue Yu

Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM rewrites existing text while applying generation-time watermarking, to protect…

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

Machine learning as a Service (MLaaS) allows users to query the machine learning model in an API manner, which provides an opportunity for users to enjoy the benefits brought by the high-performance model trained on valuable data. This…

Cryptography and Security · Computer Science 2024-04-02 Yiyong Liu , Rui Wen , Michael Backes , Yang Zhang

Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking, has been used as a principled approach to provable detection…

Statistics Theory · Mathematics 2025-08-28 Xiang Li , Feng Ruan , Huiyuan Wang , Qi Long , Weijie J. Su

Over the past two years, the use of large language models (LLMs) has advanced rapidly. While these LLMs offer considerable convenience, they also raise security concerns, as LLMs are vulnerable to adversarial attacks by some well-designed…

Computation and Language · Computer Science 2025-04-24 Guang Lin , Toshihisa Tanaka , Qibin Zhao

Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains. However,…

Cryptography and Security · Computer Science 2024-01-30 Peizhuo Lv , Pan Li , Shenchen Zhu , Shengzhi Zhang , Kai Chen , Ruigang Liang , Chang Yue , Fan Xiang , Yuling Cai , Hualong Ma , Yingjun Zhang , Guozhu Meng

Detecting machine-generated text is essential for transparency and accountability when deploying large language models (LLMs). Among detection approaches, watermarking is a statistically reliable method by design -- it embeds detectable…

Computation and Language · Computer Science 2026-05-05 Koshiro Saito , Ryuto Koike , Masahiro Kaneko , Naoaki Okazaki

The rapid advancement of generative AI has underscored the critical need for identifying image ownership and protecting copyrights. This makes post-processing image watermarking an essential tool -- it involves embedding a specific…

Cryptography and Security · Computer Science 2026-05-12 Xinyu Zhang , Ziping Dong , Qingyu Liu , Yuan Hong , Zhongjie Ba , Kui Ren

Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…

Software Engineering · Computer Science 2026-04-03 Tyler Slater