English
Related papers

Related papers: DITTO: A Spoofing Attack Framework on Watermarked …

200 papers

With the significant advances in deep generative models for image and video synthesis, Deepfakes and manipulated media have raised severe societal concerns. Conventional machine learning classifiers for deepfake detection often fail to cope…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Aakash Varma Nadimpalli , Ajita Rattani

In this paper, we investigate the recent state-of-the-art schemes for watermarking large language models (LLMs) outputs. These techniques are claimed to be robust, scalable and production-grade, aimed at promoting responsible usage of LLMs.…

Cryptography and Security · Computer Science 2026-05-11 Jonathan Hong Jin Ng , Anh Tu Ngo , Anupam Chattopadhyay

Deep learning has been achieving top performance in many tasks. Since training of a deep learning model requires a great deal of cost, we need to treat neural network models as valuable intellectual properties. One concern in such a…

Cryptography and Security · Computer Science 2019-01-21 Ryota Namba , Jun Sakuma

With the wide application of deep neural networks, it is important to verify a host's possession over a deep neural network model and protect the model. To meet this goal, various mechanisms have been designed. By embedding extra…

Cryptography and Security · Computer Science 2021-07-19 Fang-Qi Li , Shi-Lin Wang , Alan Wee-Chung Liew

The rapid adoption of large language models (LLMs), such as GPT-4 and Claude 3.5, underscores the need to distinguish LLM-generated text from human-written content to mitigate the spread of misinformation and misuse in education. One…

Machine Learning · Statistics 2025-11-11 Xingchi Li , Xiaochi Liu , Guanxun Li

Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge distillation is widely used to compress LLMs into smaller…

Machine Learning · Computer Science 2026-01-13 Ziyao Cui , Minxing Zhang , Jian Pei

Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insufficiently evaluated. Existing evaluation methods often demand…

Cryptography and Security · Computer Science 2026-04-14 Hanbo Huang , Xuan Gong , Yiran Zhang , Hao Zheng , Shiyu Liang

Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing…

Cryptography and Security · Computer Science 2025-11-13 Yunfei Yang , Xiaojun Chen , Yuexin Xuan , Zhendong Zhao , Xin Zhao , He Li

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

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

Text watermarking for large language models (LLMs) enables model owners to verify text origin and protect intellectual property. While watermarking methods for closed-source LLMs are relatively mature, extending them to open-source models…

Cryptography and Security · Computer Science 2025-10-29 Jiaqi Xue , Yifei Zhao , Mansour Al Ghanim , Shangqian Gao , Ruimin Sun , Qian Lou , Mengxin Zheng

The growing popularity of Deep Neural Networks, which often require computationally expensive training and access to a vast amount of data, calls for accurate authorship verification methods to deter unlawful dissemination of the models and…

Cryptography and Security · Computer Science 2024-01-04 Elena Rodriguez-Lois , Fernando Perez-Gonzalez

Text content created by humans or language models is often stolen or misused by adversaries. Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like…

Cryptography and Security · Computer Science 2021-12-16 Xi Yang , Jie Zhang , Kejiang Chen , Weiming Zhang , Zehua Ma , Feng Wang , Nenghai Yu

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

Efficient knowledge injection methods for Large Language Models (LLMs), such as In-Context Learning, knowledge editing, and efficient parameter fine-tuning, significantly enhance model utility on downstream tasks. However, they also pose…

Cryptography and Security · Computer Science 2026-01-23 Ziwei Zhang , Juan Wen , Wanli Peng , Zhengxian Wu , Yinghan Zhou , Yiming Xue

We study how to watermark LLM outputs, i.e. embedding algorithmically detectable signals into LLM-generated text to track misuse. Unlike the current mainstream methods that work with a fixed LLM, we expand the watermark design space by…

Machine Learning · Computer Science 2024-03-19 Xiaojun Xu , Yuanshun Yao , Yang Liu

With the increasing prevalence of Machine Learning as a Service (MLaaS) platforms, there is a growing focus on deep neural network (DNN) watermarking techniques. These methods are used to facilitate the verification of ownership for a…

Cryptography and Security · Computer Science 2024-07-19 Yuxuan Li , Sarthak Kumar Maharana , Yunhui Guo

Deep Learning (DL) models have caused a paradigm shift in our ability to comprehend raw data in various important fields, ranging from intelligence warfare and healthcare to autonomous transportation and automated manufacturing. A practical…

Cryptography and Security · Computer Science 2018-06-04 Bita Darvish Rouhani , Huili Chen , Farinaz Koushanfar

This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-content attribution. Large language models (LLMs) require substantial investments in data,…

Cryptography and Security · Computer Science 2026-05-29 Bing Liu , Shunping Wang , Yufan Zhu , Xinyi Yu , Jing Huang , Linkang Du , Hongbin Pei , Wei Luo

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily…

Cryptography and Security · Computer Science 2023-04-06 Yiming Li , Yang Bai , Yong Jiang , Yong Yang , Shu-Tao Xia , Bo Li
‹ Prev 1 4 5 6 7 8 10 Next ›