English
Related papers

Related papers: Detecting Voice Cloning Attacks via Timbre Waterma…

200 papers

Natural language processing (NLP) technology has shown great commercial value in applications such as sentiment analysis. But NLP models are vulnerable to the threat of pirated redistribution, damaging the economic interests of model…

Cryptography and Security · Computer Science 2022-11-21 Long Dai , Jiarong Mao , Xuefeng Fan , Xiaoyi Zhou

The rapid growth of Large Language Models (LLMs) has highlighted the pressing need for reliable mechanisms to verify content ownership and ensure traceability. Watermarking offers a promising path forward, but it remains limited by privacy…

Cryptography and Security · Computer Science 2026-01-21 Thomas Fargues , Ye Dong , Tianwei Zhang , Jin-Song Dong

Recent advances in large language models have raised wide concern in generating abundant plausible source code without scrutiny, and thus tracing the provenance of code emerges as a critical issue. To solve the issue, we propose CodeMark, a…

Cryptography and Security · Computer Science 2023-05-23 Wei Li , Borui Yang , Yujie Sun , Suyu Chen , Ziyun Song , Liyao Xiang , Xinbing Wang , Chenghu Zhou

Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user…

Cryptography and Security · Computer Science 2025-01-14 Kaiyi Pang , Tao Qi , Chuhan Wu , Minhao Bai , Minghu Jiang , Yongfeng Huang

Watermarking is an important copyright protection technology which generally embeds the identity information into the carrier imperceptibly. Then the identity can be extracted to prove the copyright from the watermarked carrier even after…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Sulong Ge , Zhihua Xia , Jianwei Fei , Xingming Sun , Jian Weng

The proliferation of AI-generated content has facilitated sophisticated face manipulation, severely undermining visual integrity and posing unprecedented challenges to intellectual property. In response, a common proactive defense leverages…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Haonan An , Xiaohui Ye , Guang Hua , Yihang Tao , Hangcheng Cao , Xiangyu Yu , Yuguang Fang

Solutions for defending against deepfake speech fall into two categories: proactive watermarking models and passive conventional deepfake detectors. While both address common threats, their differences in training, optimization, and…

Sound · Computer Science 2025-06-18 Chia-Hua Wu , Wanying Ge , Xin Wang , Junichi Yamagishi , Yu Tsao , Hsin-Min Wang

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

Cryptography and Security · Computer Science 2025-07-29 Xinyue Cui , Johnny Tian-Zheng Wei , Swabha Swayamdipta , Robin Jia

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…

Cryptography and Security · Computer Science 2025-09-16 Zhaoxi Zhang , Xiaomei Zhang , Yanjun Zhang , He Zhang , Shirui Pan , Bo Liu , Asif Qumer Gill , Leo Yu Zhang

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a…

Cryptography and Security · Computer Science 2026-02-24 Hyeseon An , Shinwoo Park , Suyeon Woo , Yo-Sub Han

Digital watermarking has been widely used to protect the copyright and integrity of multimedia data. Previous studies mainly focus on designing watermarking techniques that are robust to attacks of destroying the embedded watermarks.…

Cryptography and Security · Computer Science 2022-04-20 Ruowei Wang , Chenguo Lin , Qijun Zhao , Feiyu Zhu

Modern audio is created by mixing stems from different sources, raising the question: can we independently watermark each stem and recover all watermarks after separation? We study a separation-first, multi-stream watermarking…

Sound · Computer Science 2026-03-18 Houmin Sun , Zi Hu , Linxi Li , Yechen Wang , Liwei Jin , Ming Li

Deep learning based voice synthesis technology generates artificial human-like speeches, which has been used in deepfakes or identity theft attacks. Existing defense mechanisms inject subtle adversarial perturbations into the raw speech…

Sound · Computer Science 2023-05-11 Yuanda Wang , Hanqing Guo , Guangjing Wang , Bocheng Chen , Qiben Yan

The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…

Cryptography and Security · Computer Science 2024-10-25 Miranda Christ , Sam Gunn , Tal Malkin , Mariana Raykova

Digital watermarking system is a paramount for safeguarding valuable resources and information. Digital watermarks are generally imperceptible to the human eye and ear. Digital watermark can be used in video, audio and digital images for a…

Cryptography and Security · Computer Science 2012-05-30 Md. Selim Reza , Mohammed Shafiul Alam Khan , Md. Golam Robiul Alam , Serajul Islam

Protecting deep neural networks (DNNs) against intellectual property (IP) infringement has attracted an increasing attention in recent years. Recent advances focus on IP protection of generative models, which embed the watermark information…

Cryptography and Security · Computer Science 2024-04-16 Li Zhang , Yong Liu , Xinpeng Zhang , Hanzhou Wu

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

Machine Learning · Computer Science 2024-05-03 John Kirchenbauer , Jonas Geiping , Yuxin Wen , Jonathan Katz , Ian Miers , Tom Goldstein

Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and…

Cryptography and Security · Computer Science 2026-05-29 Yuexin Li , Wenjie Qu , Linyu Wu , Yulin Chen , Yufei He , Tri Cao , Bryan Hooi , Jiaheng Zhang

Language models now routinely produce text that is difficult to distinguish from human writing, raising the need for robust tools to verify content provenance. Watermarking has emerged as a promising countermeasure, with existing work…

Cryptography and Security · Computer Science 2026-02-18 Huijia Lin , Kameron Shahabi , Min Jae Song

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