Text Watermarking

Follow this topic Ask about this topic

Text watermarking studies how to embed signals in language-model outputs so they can be detected later for provenance, attribution, or message recovery. Common approaches bias token probabilities using secret keys, while semantic, structural, and byte-level methods aim to survive paraphrasing, edits, or differences between models; error-correcting codes can help recover longer payloads. Researchers evaluate detection accuracy and false alarms alongside text quality, robustness to attacks, and performance on tasks such as summarization, question answering, and code generation. The central tension is that stronger or more persistent signals can distort output or enable unwanted monitoring, while many current methods remain vulnerable to rewriting and are not yet reliable forensic evidence.

Latest papers

44 papers10 papers in the last four weeks, up 233% on the four weeks before. 0.1% of all new papers.

No Tokenizer, Still a Gap: Cross-Lingual Fairness of Homoglyph and Invisible-Character Watermarking
Oct 27, 2026Alexander Nemecek, Yuqiao Xu, Joseph Falkenburg +1Text Watermarking Robust Watermarking
Case Western Reserve University
SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification
Oct 11, 2026Alan Tang, Lifeng Wang, Gang Wu +3Text Watermarking LLM Watermarking
Huawei Technologies Co., Ltd. · Harbin Institute of Technology, Shenzhen
ByteMark: A Unified Byte-Level Watermark for Detection Across Language Models
Oct 10, 2026Xiaopu Wang, Runze LiText Watermarking LLM Watermarking
Watermarking: from Impossibility to Auditable Compliance
Oct 5, 2026Fernando Delbianco, Fernando Tohmé, Hugo AcciarriText Watermarking Robust Watermarking
Departamento de Economía, Universidad Nacional del Sur (UNS), Bahía Blanca, Argentina · Instituto de Matemática de Bahía Blanca (INMABB), CONICET–UNS, Bahía Blanca, Argentina · Departamento de Derecho, Universidad Nacional del Sur (UNS), Bahía Blanca, Argentina
SimpleMark: Fast Multi-Bit Text Watermarking under f -Divergence Constraints
Oct 5, 2026Benjamin D. Kim, Wanrong Zhang, Weitong Ruan +2Text Watermarking LLM Watermarking
Massachusetts Institute of Technology · Amazon · Stony Brook University +1
Grammar-Guided Code Watermarking with Green Temperature
Oct 4, 2026Hyundong Jin, Hyeseon An, Soohan Lim +1Text Watermarking LLM Watermarking
Department of Computer Science Yonsei University, Seoul, Republic of Korea
Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
Oct 4, 2026Haocheng Ye, Aoting Hu, Xinwei Zhang +3Text Watermarking LLM Watermarking
Nanjing University of Science and Technology · Anhui University of Technology · The Hong Kong Polytechnic University +2
Language Model Fingerprinting Requires Rethinking Watermark Teachers
Oct 3, 2026Jeongyeon Hwang, Anshul Nasery, Sewoong Oh +1Language Model Fingerprinting Fingerprint Identification
Pohang University of Science and Technology · University of Washington
Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes
Sep 30, 2026Zewei Deng, Muhammad Siddeek, Liyan Xie +4Error-Correcting Codes Text Watermarking
University of Minnesota · Google · Oakland University +2
AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks
Sep 29, 2026Thibaud Gloaguen, Robin Staab, Martin VechevText Watermarking LLM Watermarking
ETH Zurich
TTMark: Pairwise Distortion-Free Watermarking Beyond Single-Token Entropy
Sep 28, 2026Ruibo Chen, Zhengmian Hu, Donghang Lu +5Watermark Removal Detection Text Watermarking
University of Maryland, College Park · TikTok
TripPattern: A Pattern-based Text Watermarking Method for Large Language Models
Sep 11, 2026Sangjun Moon, Dasom Choi, Jingun Kwon +3Text Watermarking LLM Watermarking
Chungnam National University · Nara Institute of Science and Technology (NAIST) · Institute of Science Tokyo
Watermarks Without Verification: AI Text Watermarking After the EU AI Act
Sep 9, 2026Alexander Nemecek, Vipin Chaudhary, Erman AydayText Watermarking AI Accountability
Case Western Reserve University
WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading
Sep 2, 2026Gang-Hyun Park, Ju-Hyeong Lee, Hee-Youl Kwak +1Multi-Bit Watermarking Error-Correcting Codes
University of Ulsan, Ulsan, Republic of Korea
SemTrace: Source-Grounded Semantic Signatures for Tracing LLM Exposure to Protected Documents
Aug 30, 2026Junyan Zhang, Yudong Zeng, Yongwei Huang +3Claim Attribution in Language Models Text Watermarking
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Bosum Institute of Management Science, Shenzhen, China
OpenStamp: A Watermark for Open-Source Language Models
Aug 28, 2026Miroojin Bakshi, Saksham Rastogi, Danish PruthiText Watermarking LLM Watermarking
Indian Institute of Science · Carnegie Mellon University
Semantic Watermarking with Order-Robust Detection over Sub-sentence Units
Aug 27, 2026Abdulrahman Diaa, Jonathan Petit, Florian KerschbaumText Watermarking Robust Watermarking
University of Waterloo · Qualcomm
ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration
Jul 20, 2026Chengheng Li-Chen, Kyuhee KimText Watermarking LLM Watermarking
Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
AI Watermark Evidence Fails Forensic Readiness: An Empirical Evaluation
Jul 17, 2026Saifur Rahman Tamim, Amir Labib KhanWatermark Removal Text Watermarking
Department of Computer Science and Engineering Northern University Bangladesh
Watermark Forensics for Generative Models: An Information-Theoretic Perspective
Jul 14, 2026Xiaoyu Li, Zheng Gao, Xiaoyan Feng +3Text Watermarking LLM Watermarking
University of New South Wales · 2Griffith University
Preserving Structure, Strengthening Signals: A Grammar-Driven Approach to Optimize the Trade-off Between Quality and Detectability in Code Watermarking
Jul 11, 2026Licheng Yu, Aiwei Liu, Songze LiText Watermarking LLM Watermarking
Southeast University · Tsinghua University
Multi-Channel Spread-Spectrum Code Watermarking
Jul 7, 2026Soohyeon Choi, Debin Gao, Yue DuanText Watermarking Language Model Fingerprinting
Singapore Management University Singapore Singapore
Selective Disclosure Watermarking for Large Language Models
Jul 6, 2026Xuyang Chen, Xiang Li, Yangxinyu Xie +1Text Watermarking Privacy-Preserving Language Models
University of Pennsylvania
Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings
Jun 30, 2026Jonas Schäfer, Cezary Pilaszewicz, Gerhard WunderText Watermarking LLM Watermarking
Department of Mathematics and Computer Science Freie Universität Berlin Berlin, Germany
CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking
Jun 23, 2026Joeun Kim, HoEun Kim, Young-Sik KimText Watermarking Multi-Bit Watermarking
Department of AI DGIST Daegu, Republic of Korea
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.
"AI Watermarking": Bridging Policy Discourse and Technical Capabilities
May 25, 2026Andrés Fábrega, Arkaprabha Bhattacharya, Miranda Christ +1Text Watermarking AI Accountability
Cornell University · Columbia University · New York University
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
State University of New York at Albany · New Jersey Institute of Technology · Microsoft +1
Watermarking Should Be Treated as a Monitoring Primitive
May 13, 2026Toluwani Aremu, Jie Zhang, Nils LukasText Watermarking
MBZUAI, UAE · A*STAR, Singapore

Oct 27, 2026J/K move · Enter open · S save

No Tokenizer, Still a Gap: Cross-Lingual Fairness of Homoglyph and Invisible-Character Watermarking

Alexander Nemecek, Yuqiao Xu, Joseph Falkenburg, Erman Ayday

Case Western Reserve University

Text Watermarking Robust Watermarking Low-Resource Language Processing

Open paper AskPDF arXiv

Homoglyph and invisible-character watermarks are edit-based watermarks. Instead of changing how a model generates text, they hide a signal in the text after it is written. They swap some characters for homoglyphs, which look the same, or very similar, but have different Unicode code points, or they insert characters that do not display, all without access to the model that wrote the text. Generation-time watermarks work less well for lower-resourced languages due to how tokenizers split their text. Because they work on individual characters, these watermarks never touch a tokenizer, so we ask whether they escape this gap. Across 40 language varieties in 24 scripts, we measure capacity (the hidden bits each character can carry), how much of it survives routine handling and targeted removal, and how much text a keyed detector needs. Capacity varies 3.3-fold and script accounts for 96% of that variation. Within Latin script, resource level makes no detectable difference (

ρ=+0.095

p=0.78

), but across scripts capacity rises with it (

ρ=+0.54

, 95% CI

[+0.14,+0.83]

), because lower-resourced languages tend to use scripts with few homoglyphs. Ordinary copy-paste, which strips invisible characters, widens the gap: a detector then needs about 2 code points of English or Persian but 93 of Lao. Removing the tokenizer does not remove the inequity, but instead only changes its source.