LLM Watermarking

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 61

All topics

Global Sketch-Based Watermarking for Diffusion Language Models
Jun 3, 2026Daniel ZhaoDiffusion Model Watermarking LLM Watermarking
Harvard University
Linguistics-Aware Non-Distortionary LLM Watermarking
May 30, 2026Shinwoo Park, Hyejin Park, Hyeseon An +1LLM Watermarking
Yonsei University, Seoul, Republic of Korea · Rensselaer Polytechnic Institute, Troy, NY, USA
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
May 28, 2026Zhihao Wu, Gracia Gong, Qinglin Zhu +2Watermark Removal LLM Watermarking
Department of Informatics, King’s College London, UK · Department of Mathematics, Imperial College London, UK · Department of Statistics, University of Warwick, UK.
AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
May 28, 2026Yuexin Li, Wenjie Qu, Linyu Wu +5Text Watermarking LLM Watermarking
1National University of Singapore.
Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
May 28, 2026Bing Liu, Shunping Wang, Yufan Zhu +5Data Provenance Language Model Fingerprinting
School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, China · State Grid Henan Marketing Service Center, Henan, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China +3
Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking
May 27, 2026Ziyang You, Huilong He, Xiaoke Yang +1LLM Security LLM Watermarking
Fujian Provincial Key Laboratory of Automotive Electronics and Electric Drive, School of Electronic, Electrical and Physics, Fujian University of Technology, Fuzhou 350118, China · School of Humanities, Fujian University of Technology, Fuzhou 350118, China · Institute of Applied Physics and Materials Engineering, University of Macau, Macau 999078, China
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
May 27, 2026Jiacheng Lu, Yiming Li, Tao Song +4LLM Watermarking Robust Watermarking
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Nanyang Technological University, Singapore · National University of Singapore, Singapore
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
May 25, 2026Jiahao Huo, Wenjie Qu, Yibo Yan +5Text Watermarking LLM Watermarking
The Hong Kong University of Science and Technology (Guangzhou) · National University of Singapore · The Hong Kong University of Science and Technology +1
Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection
May 22, 2026Kieu Dang, Phung Lai, NhatHai Phan +2Text Watermarking Language Model Fingerprinting
1State University of New York at Albany · 2New Jersey Institute of Technology · 3Microsoft +1
Asking Back: Interaction-Layer Antidistillation Watermarks
May 15, 2026Guang Yang, Amir Ghasemian, Fengchen Liu +3LLM Auditing LLM Watermarking
University of California, Los Angeles · Lawrence Berkeley National Laboratory · Meta
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
May 12, 2026Tom Sander, Hongyan Chang, Tomáš Souček +10Language Model Fingerprinting LLM Watermarking
FAIR, Meta Superintelligence Labs
Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
May 12, 2026Thibaud Gloaguen, Robin Staab, Mark Vero +1Text Watermarking LLM Watermarking
ETH Zurich
Sequential Behavioral Watermarking for LLM Agents
May 11, 2026Hyeseon An, Shinwoo Park, Dongsu Kim +1LLM Watermarking LLM Agents
Department of Computer Science Yonsei University Seoul, South Korea
Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents
May 9, 2026Carol Xuan LongMulti-Agent LLM Systems AI Accountability
John A. Paulson School Of Engineering And Applied Sciences, Harvard University, Cambridge, Massachusetts
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
May 9, 2026Zhenxin Ai, Haiyun HeLLM Watermarking Robust Watermarking
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China.
Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
May 8, 2026Jonathan Hong Jin Ng, Anh Tu Ngo, Anupam ChattopadhyayWatermark Removal LLM Watermarking
College of Computing and Data Science Nanyang Technological University Singapore
Dataset Watermarking for Closed LLMs with Provable Detection
May 7, 2026Pengrun Huang, Kamalika Chaudhuri, Yu-Xiang WangDataset Watermarking LLM Auditing
Preprint. Under review.
Detecting Verbatim LLM Copy-Paste in Homework
May 7, 2026Aizierjiang AiersilanText Watermarking AI-Generated Text Detection
The George Washington University
Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks
May 6, 2026Mohd Ruhul Ameen, Akif Islam, Nadim Mahmud +1Diffusion Model Watermarking Watermark Removal
College of Engineering and Computer Science, Marshall University, Huntington, WV, USA · Department of Computer Science and Engineering, University of Rajshahi, Rajshahi, Bangladesh · Miami University, Oxford, OH 45056, USA
SLAM: Structural Linguistic Activation Marking for Language Models
May 6, 2026Fabrice Harel-Canada, Amit SahaiLLM Watermarking Robust Watermarking
University of California, Los Angeles
SWAN: Semantic Watermarking with Abstract Meaning Representation
May 5, 2026Ziping Ye, Gourab Dey, Christos Christodoulopoulos +7Text Watermarking LLM Watermarking
1Amazon · 2Information Commissioner’s Office · 3Meta +2
LLM Output Detectability and Task Performance Can be Jointly Optimized
May 2, 2026Koshiro Saito, Ryuto Koike, Masahiro Kaneko +1AI-Generated Text Detection LLM Watermarking
Institute of Science Tokyo · MBZUAI · National Institute of Advanced Industrial Science and Technology +1
Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
May 1, 2026Joeun Kim, HoEun Kim, Dongsup Jin +1Text Watermarking LLM Watermarking
Department of AI, DGIST, Daegu, Republic of Korea · Department of ICT Convergence, University of Ulsan, Ulsan, Republic of Korea · Department of EECS, DGIST, Daegu, Republic of Korea
SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking
Apr 24, 2026Chenxi Gu, Xiaoning Du, John GrundyLLM Watermarking
Monash University
SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models
Apr 18, 2026Yifei Zhao, Qian Lou, Mengxin ZhengVLM Robustness Language Model Fingerprinting
University of Central Florida
Watermarking Diffusion Language Models
Sep 29, 2025Thibaud Gloaguen, Robin Staab, Nikola Jovanović +1Diffusion Model Watermarking LLM Watermarking
ETH Zurich
Fast segmentation of watermarked texts from large language models through an epidemic change-point framework
Sep 25, 2025Soham Bonnerjee, Subhrajyoty Roy, Sayar KarmakarText Watermarking LLM Watermarking
University of Chicago · Washington University in St. Louis · University of Florida
Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
Jun 27, 2025Xiang Li, Garrett Wen, Weiqing He +3Text Watermarking Minimax Estimation
University of Pennsylvania · Yale University
Optimizing watermarks for large language models
Dec 28, 2023Bram WoutersLLM Watermarking Robust Watermarking
University of Amsterdam
Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation
Date pendingAsim Mohamed, Martin GubriMultilingual Language Model Evaluation LLM Watermarking
Parameter Lab · École Polytechnique, IP Paris, CNRS

Jun 3, 2026, cs.CRJ/K move · Enter open · S save

Global Sketch-Based Watermarking for Diffusion Language Models

Daniel Zhao

Harvard University

Diffusion Model Watermarking LLM Watermarking Robust Watermarking Diffusion Language Models

Open paper AskPDF arXiv

Watermarking methods for language models have been studied extensively in the autoregressive setting, where tokens are generated sequentially. These works largely focus on local-context schemes that perturb the next token's distribution as a function of its preceding tokens. In diffusion language models, distributions over many unresolved positions are jointly sampled, allowing additive statistics of the entire sequence to be tractable during generation. We propose a watermark for masked diffusion language models that controls a global, vector-valued sketch representation of the text. Compared to context-dependent watermarking, the sketch formulation decouples detection from the local contexts seen during generation, resulting in an order-agnostic statistic and a watermarking rule which does not manifest as a simple token bias. We analyze the distortion, soundness, and robustness properties of the method.

Momentum

Related topics

Latest papers 61