English
Related papers

Related papers: $B^4$: A Black-Box Scrubbing Attack on LLM Waterma…

200 papers

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

Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text…

Cryptography and Security · Computer Science 2024-10-21 Eva Giboulot , Teddy Furon

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely…

Cryptography and Security · Computer Science 2024-07-25 Xuhong Wang , Haoyu Jiang , Yi Yu , Jingru Yu , Yilun Lin , Ping Yi , Yingchun Wang , Yu Qiao , Li Li , Fei-Yue Wang

Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs,…

Cryptography and Security · Computer Science 2024-12-09 Lingjie Chen , Ruizhong Qiu , Siyu Yuan , Zhining Liu , Tianxin Wei , Hyunsik Yoo , Zhichen Zeng , Deqing Yang , Hanghang Tong

Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechanisms by designing watermark removal attacks. However, these…

Cryptography and Security · Computer Science 2021-05-18 Shangwei Guo , Tianwei Zhang , Han Qiu , Yi Zeng , Tao Xiang , Yang Liu

With the rapid development of cloud-based services, large language models have become increasingly accessible through various web platforms. However, this accessibility has also led to growing risks of model abuse. LLM watermarking has…

Cryptography and Security · Computer Science 2026-04-28 Hao Li , Yubing Ren , Yanan Cao , Yingjie Li , Fang Fang , Shi Wang , Li Guo

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to…

Cryptography and Security · Computer Science 2025-01-29 Aiwei Liu , Sheng Guan , Yiming Liu , Leyi Pan , Yifei Zhang , Liancheng Fang , Lijie Wen , Philip S. Yu , Xuming Hu

LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up…

Cryptography and Security · Computer Science 2026-02-09 Thibaud Gloaguen , Robin Staab , Nikola Jovanović , Martin Vechev

With the development of deep learning, high-value and high-cost models have become valuable assets, and related intellectual property protection technologies have become a hot topic. However, existing model watermarking work in black-box…

Cryptography and Security · Computer Science 2024-04-16 Na Zhao , Kejiang Chen , Weiming Zhang , Nenghai Yu

Recent years have seen a surge in interest in digital content watermarking techniques, driven by the proliferation of generative models and increased legal pressure. With an ever-growing percentage of AI-generated content available online,…

As open-source large language models (LLMs) like Llama3 become more capable, it is crucial to develop watermarking techniques to detect their potential misuse. Existing watermarking methods either add watermarks during LLM inference, which…

Computation and Language · Computer Science 2025-03-18 Yijie Xu , Aiwei Liu , Xuming Hu , Lijie Wen , Hui Xiong

Watermarking is a promising defense against the misuse of large language models (LLMs), yet it remains vulnerable to scrubbing and spoofing attacks. This vulnerability stems from an inherent trade-off governed by watermark window size:…

Cryptography and Security · Computer Science 2025-12-09 Huanming Shen , Baizhou Huang , Xiaojun Wan

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

Safeguarding the intellectual property of machine learning models has emerged as a pressing concern in AI security. Model watermarking is a powerful technique for protecting ownership of machine learning models, yet its reliability has been…

Cryptography and Security · Computer Science 2024-09-11 Aoting Hu , Yanzhi Chen , Renjie Xie , Adrian Weller

We consider the emerging problem of identifying the presence and use of watermarking schemes in widely used, publicly hosted, closed source large language models (LLMs). We introduce a suite of baseline algorithms for identifying watermarks…

Machine Learning · Computer Science 2023-05-31 Leonard Tang , Gavin Uberti , Tom Shlomi

Watermarking is a key technique for detecting AI-generated text. In this work, we study its vulnerabilities and introduce the Smoothing Attack, a novel watermark removal method. By leveraging the relationship between the model's confidence…

Machine Learning · Computer Science 2025-02-06 Hongyan Chang , Hamed Hassani , Reza Shokri

Due to the distributed nature of Federated Learning (FL) systems, each local client has access to the global model, which poses a critical risk of model leakage. Existing works have explored injecting watermarks into local models to enable…

Cryptography and Security · Computer Science 2026-02-10 Jiahao Xu , Rui Hu , Olivera Kotevska , Zikai Zhang

Box-free model watermarking is an emerging technique to safeguard the intellectual property of deep learning models, particularly those for low-level image processing tasks. Existing works have verified and improved its effectiveness in…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Haonan An , Guang Hua , Zhiping Lin , Yuguang Fang

Advances in generative models have made it possible for AI-generated text, code, and images to mirror human-generated content in many applications. Watermarking, a technique that aims to embed information in the output of a model to verify…

Cryptography and Security · Computer Science 2024-11-14 Qi Pang , Shengyuan Hu , Wenting Zheng , Virginia Smith

Language models (LMs) have emerged as critical intellectual property (IP) assets that necessitate protection. Although various watermarking strategies have been proposed, they remain vulnerable to Linear Functionality Equivalence Attack…

Cryptography and Security · Computer Science 2025-02-04 Haodong Zhao , Jinming Hu , Peixuan Li , Fangqi Li , Jinrui Sha , Tianjie Ju , Peixuan Chen , Zhuosheng Zhang , Gongshen Liu