English
Related papers

Related papers: Watermark Stealing in Large Language Models

200 papers

Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…

Computation and Language · Computer Science 2024-03-26 Masahiro Kaneko , Timothy Baldwin

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…

Machine Learning · Computer Science 2025-05-22 Zhuang Li , Qiuping Yi , Zongcheng Ji , Yijian Lu , Yanqi Li , Keyang Xiao , Hongliang Liang

Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability…

Computation and Language · Computer Science 2024-06-07 Liang Chen , Yatao Bian , Yang Deng , Deng Cai , Shuaiyi Li , Peilin Zhao , Kam-fai Wong

In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outputs on specific input patterns while maintaining clean…

Cryptography and Security · Computer Science 2026-05-14 Jagadeesh Rachapudi , Ritali Vatsi , Pranav Singh , Praful Hambarde , Amit Shukla

Watermarking technology has gained significant attention due to the increasing importance of intellectual property (IP) rights, particularly with the growing deployment of large language models (LLMs) on billions resource-constrained edge…

Cryptography and Security · Computer Science 2025-07-14 Qingxiao Guo , Xinjie Zhu , Yilong Ma , Hui Jin , Yunhao Wang , Weifeng Zhang , Xiaobing Guo

LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for detection with measurable quality loss. We present SLAM (Structural Linguistic Activation Marking),…

Computation and Language · Computer Science 2026-05-12 Fabrice Harel-Canada , Amit Sahai

Natural language generation (NLG) applications have gained great popularity due to the powerful deep learning techniques and large training corpus. The deployed NLG models may be stolen or used without authorization, while watermarking has…

Multimedia · Computer Science 2021-12-13 Tao Xiang , Chunlong Xie , Shangwei Guo , Jiwei Li , Tianwei Zhang

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

Cryptography and Security · Computer Science 2024-04-23 Hongyu Zhu , Sichu Liang , Wentao Hu , Fangqi Li , Ju Jia , Shilin Wang

As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms. Existing watermark techniques are shown effective in…

Machine Learning · Computer Science 2024-08-09 Chaoyi Zhu , Jeroen Galjaard , Pin-Yu Chen , Lydia Y. Chen

Watermarking approaches are proposed to identify if text being circulated is human or large language model (LLM) generated. The state-of-the-art watermarking strategy of Kirchenbauer et al. (2023a) biases the LLM to generate specific…

Cryptography and Security · Computer Science 2024-03-25 Qilong Wu , Varun Chandrasekaran

Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models (LMs). However, the robustness of the watermarking schemes has not been…

Computation and Language · Computer Science 2025-07-04 Ruibo Chen , Yihan Wu , Junfeng Guo , Heng Huang

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

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…

Cryptography and Security · Computer Science 2025-11-17 Yanbo Dai , Zongjie Li , Zhenlan Ji , Shuai Wang

A key component of generating text from modern language models (LM) is the selection and tuning of decoding algorithms. These algorithms determine how to generate text from the internal probability distribution generated by the LM. The…

Machine Learning · Computer Science 2023-12-05 Ali Naseh , Kalpesh Krishna , Mohit Iyyer , Amir Houmansadr

In recent years, tremendous success has been witnessed in Retrieval-Augmented Generation (RAG), widely used to enhance Large Language Models (LLMs) in domain-specific, knowledge-intensive, and privacy-sensitive tasks. However, attackers may…

Cryptography and Security · Computer Science 2025-01-10 Peizhuo Lv , Mengjie Sun , Hao Wang , Xiaofeng Wang , Shengzhi Zhang , Yuxuan Chen , Kai Chen , Limin Sun

We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts generated by large language models (LLMs). Synthesizing human-like content using LLMs necessitates vast computational resources and extensive…

Cryptography and Security · Computer Science 2024-04-09 Ruisi Zhang , Shehzeen Samarah Hussain , Paarth Neekhara , Farinaz Koushanfar

With the increasing use of large language models (LLMs) in daily life, concerns have emerged regarding their potential misuse and societal impact. Watermarking is proposed to trace the usage of specific models by injecting patterns into…

Cryptography and Security · Computer Science 2024-05-24 Baizhou Huang , Xiaojun Wan

Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they are evaluated only on high-resource languages. We…

Computation and Language · Computer Science 2026-03-26 Asim Mohamed , Martin Gubri

Text watermarking algorithms for large language models (LLMs) can effectively identify machine-generated texts by embedding and detecting hidden features in the text. Although the current text watermarking algorithms perform well in most…

Computation and Language · Computer Science 2024-06-11 Yijian Lu , Aiwei Liu , Dianzhi Yu , Jingjing Li , Irwin King

To address the challenging problem of detecting phishing webpages, researchers have developed numerous solutions, in particular those based on machine learning (ML) algorithms. Among these, brand-based phishing detection that uses models…

Cryptography and Security · Computer Science 2024-08-13 Jehyun Lee , Peiyuan Lim , Bryan Hooi , Dinil Mon Divakaran