English
Related papers

Related papers: PVMark: Enabling Public Verifiability for LLM Wate…

200 papers

This paper presents a novel approach to deter unauthorized deepfakes and enable user tracking in generative models, even when the user has full access to the model parameters, by integrating key-based model authentication with watermarking…

Cryptography and Security · Computer Science 2024-09-24 Mayank Kumar Singh , Naoya Takahashi , Wei-Hsiang Liao , Yuki Mitsufuji

This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information…

Cryptography and Security · Computer Science 2025-07-03 Haiyun He , Yepeng Liu , Ziqiao Wang , Yongyi Mao , Yuheng Bu

The advent of video-based Large Language Models (LLMs) has significantly enhanced video understanding. However, it has also raised some safety concerns regarding data protection, as videos can be more easily annotated, even without…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Jinmin Li , Kuofeng Gao , Yang Bai , Jingyun Zhang , Shu-Tao Xia

Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine learning-based detectors that predict if text is synthetic,…

Machine Learning · Computer Science 2025-04-17 David Khachaturov , Robert Mullins , Ilia Shumailov , Sumanth Dathathri

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

The widespread use of Large Language Models (LLMs) in text generation has raised increasing concerns about intellectual property disputes. Watermarking techniques, which embed meta information into AI-generated content (AIGC), have the…

Cryptography and Security · Computer Science 2026-04-15 Shangkun Che , Silin Du , Ge Gao

Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related to intellectual property. In this context, we focus on model stealing attacks, where…

Cryptography and Security · Computer Science 2025-10-28 Kieu Dang , Phung Lai , NhatHai Phan , Yelong Shen , Ruoming Jin , Abdallah Khreishah

We show the viability of tackling misuses of large language models beyond the identification of machine-generated text. While existing zero-bit watermark methods focus on detection only, some malicious misuses demand tracing the adversary…

Computation and Language · Computer Science 2024-03-21 KiYoon Yoo , Wonhyuk Ahn , Nojun Kwak

In last years, there has been an increasing effort to leverage Distributed Ledger Technology (DLT), including blockchain. One of the main topics of interest, given its importance, is the research and development of privacy mechanisms, as…

Cryptography and Security · Computer Science 2019-07-16 Eduardo Morais , Tommy Koens , Cees van Wijk , Aleksei Koren

The proliferation of open-source code and large language models (LLMs) for code generation has amplified the risks of unauthorized reuse and intellectual property infringement. Source code watermarking offers a potential solution, yet…

Cryptography and Security · Computer Science 2026-04-21 Rui Xu , Jiawei Chen , Weizhi Liu , Zhaoxia Yin , Cong Kong , Xinpeng Zhang

In federated learning (FL), $K$ clients jointly train a model without sharing raw data. Because each participant invests data and compute, clients need mechanisms to later prove the provenance of a jointly trained model. Model watermarking…

Machine Learning · Computer Science 2026-05-29 Tameem Bakr , Anish Ambreth , Nils Lukas

This paper focuses on investigation of confidential documents leaks in the form of screen photographs. Proposed approach does not try to prevent leak in the first place but rather aims to determine source of the leak. Method works by…

Cryptography and Security · Computer Science 2023-04-26 Aleksey Yakushev , Yury Markin , Dmitry Obydenkov , Alexander Frolov , Stas Fomin , Manuk Akopyan , Alexander Kozachok , Arthur Gaynov

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 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 progress in large language models enables the creation of realistic machine-generated content. Watermarking is a promising approach to distinguish machine-generated text from human text, embedding statistical signals in the output…

Cryptography and Security · Computer Science 2026-02-25 Patrick Chao , Yan Sun , Edgar Dobriban , Hamed Hassani

Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fully watermarked text from non-watermarked text, overlooking…

Computation and Language · Computer Science 2025-02-25 Leyi Pan , Aiwei Liu , Yijian Lu , Zitian Gao , Yichen Di , Shiyu Huang , Lijie Wen , Irwin King , Philip S. Yu

Deepfake facial manipulation has garnered significant public attention due to its impacts on enhancing human experiences and posing privacy threats. Despite numerous passive algorithms that have been attempted to thwart malicious Deepfake…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Tianyi Wang , Mengxiao Huang , Harry Cheng , Xiao Zhang , Zhiqi Shen

To mitigate the potential misuse of large language models (LLMs), recent research has developed watermarking algorithms, which restrict the generation process to leave an invisible trace for watermark detection. Due to the two-stage nature…

Computation and Language · Computer Science 2024-07-02 Shangqing Tu , Yuliang Sun , Yushi Bai , Jifan Yu , Lei Hou , Juanzi Li

Watermarking has become a plausible candidate for ownership verification and intellectual property protection of deep neural networks. Regarding image classification neural networks, current watermarking schemes uniformly resort to backdoor…

Cryptography and Security · Computer Science 2022-04-12 Fangqi Li , Shilin Wang

Voice cloning (VC)-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by training them on watermarked audio but fail in zero-shot VC…

Sound · Computer Science 2025-06-02 Haiyun Li , Zhiyong Wu , Xiaofeng Xie , Jingran Xie , Yaoxun Xu , Hanyang Peng