English
Related papers

Related papers: Undetectable Watermarks for Language Models

200 papers

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

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 the outputs of large language models (LLMs) is critical for provenance tracing, content regulation, and model accountability. Existing approaches often rely on access to model internals or are constrained by static rules and…

Machine Learning · Computer Science 2025-06-23 Agnibh Dasgupta , Abdullah Tanvir , Xin Zhong

Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property. The literature has shown great interest in attacks on watermarking schemes: attackers are…

Cryptography and Security · Computer Science 2026-05-19 Maria Bulychev , Neil G. Marchant , Benjamin I. P. Rubinstein

Recent advances in Large Language Models (LLMs) have raised urgent concerns about LLM-generated text authenticity, prompting regulatory demands for reliable identification mechanisms. Although watermarking offers a promising solution,…

Computation and Language · Computer Science 2025-08-26 Xiaoyan Feng , He Zhang , Yanjun Zhang , Leo Yu Zhang , Shirui Pan

Deep neural networks have recently achieved significant progress. Sharing trained models of these deep neural networks is very important in the rapid progress of researching or developing deep neural network systems. At the same time, it is…

Computer Vision and Pattern Recognition · Computer Science 2018-02-07 Yusuke Uchida , Yuki Nagai , Shigeyuki Sakazawa , Shin'ichi Satoh

Statistical watermarking techniques are well-established for sequentially decoded language models (LMs). However, these techniques cannot be directly applied to order-agnostic LMs, as the tokens in order-agnostic LMs are not generated…

Computation and Language · Computer Science 2024-10-18 Ruibo Chen , Yihan Wu , Yanshuo Chen , Chenxi Liu , Junfeng Guo , Heng Huang

The rapid growth of transformer-based models increases the concerns about their integrity and ownership insurance. Watermarking addresses this issue by embedding a unique identifier into the model, while preserving its performance. However,…

Cryptography and Security · Computer Science 2024-01-19 Pierre Fernandez , Guillaume Couairon , Teddy Furon , Matthijs Douze

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately detect LLM-generated…

Computation and Language · Computer Science 2025-11-19 William Guo , Adaku Uchendu , Ana Smith

As large language models (LLMs) grow more powerful, concerns over copyright infringement of LLM-generated texts have intensified. LLM watermarking has been proposed to trace unauthorized redistribution or resale of generated content by…

Cryptography and Security · Computer Science 2025-08-05 Qihao Lin , Chen Tang , Lan zhang , Junyang zhang , Xiangyang Li

Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a…

Sound · Computer Science 2022-03-16 Yongbaek Cho , Changhoon Kim , Yezhou Yang , Yi Ren

Speech watermarking techniques can proactively mitigate the potential harmful consequences of instant voice cloning techniques. These techniques involve the insertion of signals into speech that are imperceptible to humans but can be…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-19 Shengpeng Ji , Ziyue Jiang , Jialong Zuo , Minghui Fang , Yifu Chen , Tao Jin , Zhou Zhao

LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized third party forges the watermark, enabling it to falsely…

Cryptography and Security · Computer Science 2025-05-23 Thibaud Gloaguen , Nikola Jovanović , Robin Staab , Martin Vechev

Code datasets are of immense value for training neural-network-based code completion models, where companies or organizations have made substantial investments to establish and process these datasets. Unluckily, these datasets, either built…

Software Engineering · Computer Science 2023-08-29 Zhensu Sun , Xiaoning Du , Fu Song , Li Li

In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Jijia Yang , Sen Peng , Xiaohua Jia

Recent advancements in large language models (LLMs) have highlighted the risk of misusing them, raising the need for accurate detection of LLM-generated content. In response, a viable solution is to inject imperceptible identifiers into…

Computation and Language · Computer Science 2025-02-11 Minjia Mao , Dongjun Wei , Zeyu Chen , Xiao Fang , Michael Chau

Watermarks should be introduced in the natural language outputs of AI systems in order to maintain the distinction between human and machine-generated text. The ethical imperative to not blur this distinction arises from the asemantic…

Computation and Language · Computer Science 2022-09-08 Alexei Grinbaum , Laurynas Adomaitis

A generative AI model can generate extremely realistic-looking content, posing growing challenges to the authenticity of information. To address the challenges, watermark has been leveraged to detect AI-generated content. Specifically, a…

Machine Learning · Computer Science 2023-11-09 Zhengyuan Jiang , Jinghuai Zhang , Neil Zhenqiang Gong

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

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
‹ Prev 1 3 4 5 6 7 10 Next ›