English
Related papers

Related papers: MC$^2$Mark: Distortion-Free Multi-Bit Watermarking…

200 papers

We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking…

Computer Vision and Pattern Recognition · Computer Science 2022-03-24 Pierre Fernandez , Alexandre Sablayrolles , Teddy Furon , Hervé Jégou , Matthijs Douze

Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts. Watermarking is pivotal in this context, which involves…

Machine Learning · Computer Science 2024-06-07 Mingjia Huo , Sai Ashish Somayajula , Youwei Liang , Ruisi Zhang , Farinaz Koushanfar , Pengtao Xie

We study the problem of multi-bit watermarking for large language models (LLMs). We introduce a block-autoregressive model inspired by multi-token prediction, in which the encoder has limited non-causal access to token distributions within…

Information Theory · Computer Science 2026-05-19 Sidong Guo , Tyler Kann , Teodora Baluta , Matthieu R. Bloch

As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text watermarking techniques have proven reliable in distinguishing…

Computation and Language · Computer Science 2024-04-04 Lean Wang , Wenkai Yang , Deli Chen , Hao Zhou , Yankai Lin , Fandong Meng , Jie Zhou , Xu Sun

As large language models become standard backends for content generation, practical provenance increasingly requires multi-bit watermarking. In provider-internal deployments, a key requirement is message symmetry: the message itself should…

Computation and Language · Computer Science 2026-04-16 Junlin Zhu , Baizhou Huang , Xiaojun Wan

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

The development of large language models (LLMs) has raised concerns about potential misuse. One practical solution is to embed a watermark in the text, allowing ownership verification through watermark extraction. Existing methods primarily…

Cryptography and Security · Computer Science 2025-03-04 Yuhang Cai , Yaofei Wang , Donghui Hu , Chen Gu

Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. However, these contents are susceptible to…

Computation and Language · Computer Science 2023-06-12 KiYoon Yoo , Wonhyuk Ahn , Jiho Jang , Nojun Kwak

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

Computation and Language · Computer Science 2026-05-29 Yukang Lin , Jiahao Shao , Shuoran Jiang , Wentao Zhu , Bingjie Lu , Xiangping Wu , Joanna Siebert , Qingcai Chen

Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge in the domain lies in preserving the distribution of original…

Cryptography and Security · Computer Science 2024-06-26 Yihan Wu , Zhengmian Hu , Junfeng Guo , Hongyang Zhang , Heng Huang

Potential harms of Large Language Models such as mass misinformation and plagiarism can be partially mitigated if there exists a reliable way to detect machine generated text. In this paper, we propose a new watermarking method to detect…

Computation and Language · Computer Science 2023-12-12 Kaan Efe Keleş , Ömer Kaan Gürbüz , Mucahid Kutlu

The rapid advancement of LLMs (Large Language Models) has established them as a foundational technology for many AI and ML-powered human computer interactions. A critical challenge in this context is the attribution of LLM-generated text --…

Cryptography and Security · Computer Science 2026-02-27 Jarosław Janas , Paweł Morawiecki , Josef Pieprzyk

Watermarking language models is essential for distinguishing between human and machine-generated text and thus maintaining the integrity and trustworthiness of digital communication. We present a novel green/red list watermarking approach…

Machine Learning · Statistics 2025-06-13 Yangxinyu Xie , Xiang Li , Tanwi Mallick , Weijie J. Su , Ruixun Zhang

The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits,…

Machine Learning · Computer Science 2024-10-14 Yapei Chang , Kalpesh Krishna , Amir Houmansadr , John Wieting , Mohit Iyyer

Video watermarking embeds a message into a cover video in an imperceptible manner, which can be retrieved even if the video undergoes certain modifications or distortions. Traditional watermarking methods are often manually designed for…

Multimedia · Computer Science 2021-04-27 Xiyang Luo , Yinxiao Li , Huiwen Chang , Ce Liu , Peyman Milanfar , Feng Yang

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

Watermarking is one of the most important copyright protection tools for digital media. The most challenging type of watermarking is the imperceptible one, which embeds identifying information in the data while retaining the latter's…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Natan Semyonov , Rami Puzis , Asaf Shabtai , Gilad Katz

This paper introduces EmMark,a novel watermarking framework for protecting the intellectual property (IP) of embedded large language models deployed on resource-constrained edge devices. To address the IP theft risks posed by malicious…

Cryptography and Security · Computer Science 2024-02-29 Ruisi Zhang , Farinaz Koushanfar

Modern generative diffusion models rely on vast training datasets, often including images with uncertain ownership or usage rights. Radioactive watermarks -- marks that transfer to a model's outputs -- can help detect when such unauthorized…

Cryptography and Security · Computer Science 2025-12-02 Kexin Li , Guozhen Ding , Ilya Grishchenko , David Lie

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-16 Wanying Ge , Xin Wang , Junichi Yamagishi