Image de couverture de livre

No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pang, Qi, Hu, Shengyuan, Zheng, Wenting, Smith, Virginia
Format:	Preprint
Publié:	2024
Sujets:	Cryptography and Security Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Watermark under Fire: A Robustness Evaluation of LLM Watermarking
par: Liang, Jiacheng, et autres
Publié: (2024)

Downstream Trade-offs of a Family of Text Watermarks
par: Ajith, Anirudh, et autres
Publié: (2023)

Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
par: Zhang, Hanlin, et autres
Publié: (2023)

PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
par: Duan, Haohua, et autres
Publié: (2025)

A Transfer Attack to Image Watermarks
par: Hu, Yuepeng, et autres
Publié: (2024)

On the Learnability of Watermarks for Language Models
par: Gu, Chenchen, et autres
Publié: (2023)

TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
par: Sander, Tom, et autres
Publié: (2026)

Revisiting the Robustness of Watermarking to Paraphrasing Attacks
par: Rastogi, Saksham, et autres
Publié: (2024)

A Watermark for Large Language Models
par: Kirchenbauer, John, et autres
Publié: (2023)

Watermarking Needs Input Repetition Masking
par: Khachaturov, David, et autres
Publié: (2025)

On the Reliability of Watermarks for Large Language Models
par: Kirchenbauer, John, et autres
Publié: (2023)

Publicly-Detectable Watermarking for Language Models
par: Fairoze, Jaiden, et autres
Publié: (2023)

Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge
par: Cui, Xinyue, et autres
Publié: (2025)

FreqMark: Frequency-Based Watermark for Sentence-Level Detection of LLM-Generated Text
par: Xu, Zhenyu, et autres
Publié: (2024)

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
par: Wu, Yihan, et autres
Publié: (2023)

Watermarking Language Models through Language Models
par: Dasgupta, Agnibh, et autres
Publié: (2024)

Topic-Based Watermarks for Large Language Models
par: Nemecek, Alexander, et autres
Publié: (2024)

Watermarking Language Models with Error Correcting Codes
par: Chao, Patrick, et autres
Publié: (2024)

A Watermark for Black-Box Language Models
par: Bahri, Dara, et autres
Publié: (2024)

Robust Distortion-free Watermarks for Language Models
par: Kuditipudi, Rohith, et autres
Publié: (2023)

Watermarks for Embeddings-as-a-Service Large Language Models
par: Shetty, Anudeex
Publié: (2025)

Optimal Detection for Language Watermarks with Pseudorandom Collision
par: Cai, T. Tony, et autres
Publié: (2025)

Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
par: He, Weiqing, et autres
Publié: (2026)

Towards Optimal Statistical Watermarking
par: Huang, Baihe, et autres
Publié: (2023)

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
par: Rastogi, Saksham, et autres
Publié: (2025)

Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
par: Xu, Yijie, et autres
Publié: (2025)

Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
par: Huo, Mingjia, et autres
Publié: (2024)

WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
par: Shetty, Anudeex, et autres
Publié: (2024)

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
par: Shetty, Anudeex, et autres
Publié: (2024)

Watermarking LLM Agent Trajectories
par: Meng, Wenlong, et autres
Publié: (2026)

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks
par: Liu, Zesen, et autres
Publié: (2024)

Watermarking Makes Language Models Radioactive
par: Sander, Tom, et autres
Publié: (2024)

Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign
par: Zhang, Ruisi, et autres
Publié: (2025)

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
par: Liu, Bing, et autres
Publié: (2026)

Debiasing Watermarks for Large Language Models via Maximal Coupling
par: Xie, Yangxinyu, et autres
Publié: (2024)

Duwak: Dual Watermarks in Large Language Models
par: Zhu, Chaoyi, et autres
Publié: (2024)

WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness
par: Huang, Baizhou, et autres
Publié: (2024)

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking
par: Zhao, Yizhou, et autres
Publié: (2025)

From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
par: Wang, Yidan, et autres
Publié: (2025)

PostMark: A Robust Blackbox Watermark for Large Language Models
par: Chang, Yapei, et autres
Publié: (2024)