LLM Watermarking

LLM: Large Language Model

Large language model watermarking studies how to mark generated text, model behavior, or model parameters so that provenance, ownership, or use of protected data can later be checked. Common approaches add keyed statistical patterns to token sampling, encode messages with error-correcting codes, or place signals in semantic structure, model weights, activations, and agent actions. Researchers evaluate detection and message recovery alongside text quality, false-positive rates, and resistance to paraphrasing, translation, editing, fine-tuning, and other attacks. The central tension is making marks reliable and hard to forge or remove without harming usefulness, while ensuring detection remains trustworthy at real-world scale.

Latest papers

112 papers26 papers in the last four weeks, up 189% on the four weeks before. 0.2% of all new papers.

Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models
Apr 13, 2026Shuhao Zhang, Yuli Chen, Jiale Han +2Adversarial Attacks on LLMs LLM Watermarking
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications · Hong Kong University of Science and Technology
Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints
Apr 9, 2026Yu-Shin Huang, Chao Tian, Krishna NarayananMulti-Bit Watermarking Text Watermarking
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
Apr 6, 2026Jiahao Xu, Rui Hu, Olivera Kotevska +1Multi-Bit Watermarking Text Watermarking
University of Nevada, Reno · Oak Ridge National Laboratory
Refined Detection for Gumbel Watermarking
Mar 31, 2026Tor LattimoreWatermark Removal Detection Text Watermarking
Google DeepMind
Transparency as Architecture: Structural Compliance Gaps in EU AI Act Article 50 II
Mar 27, 2026Vera Schmitt, Niklas Kruse, Premtim Sahitaj +1AI Regulatory Compliance AI Governance
Technichal University Berlin XpaliNLP Group · Research Center for Artificial Intelligence (DFKI) Berlin · Center for European Research on Trusted AI (CERTAIN) +1
Adaptively Robust LLM Monitoring via Activation Watermarking
Mar 24, 2026Toluwani Aremu, Daniil Ognev, Samuele Poppi +1LLM Auditing LLM Watermarking
Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)
Functional Subspace Watermarking for Large Language Models
Mar 19, 2026Zikang Ding, Junhao Li, Suling Wu +3LLM Watermarking Robust Watermarking
University of Electronic Science and Technology of China, Chengdu, China · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates · South China University of Technology, Guangzhou, China
Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
Mar 16, 2026Zhuoshang Wang, Yubing Ren, Yanan Cao +3LLM Watermarking Robust Watermarking
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · National Computer Network Emergency Response Technical Team, Coordination Center of China (CNCERT/CC), Beijing, China
On Google's SynthID-Text LLM Watermarking System: Theoretical Analysis and Empirical Validation
Mar 3, 2026Romina Omidi, Yun Dong, Binghui WangLLM Watermarking Robust Watermarking
Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA
Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMs
Feb 21, 2026Chengwei Xia, Fan Ma, Ruijie Quan +3LLM Watermarking Adversarial Examples
School of Information Science and Engineering, Lanzhou University · College of Computer Science and Technology, Zhejiang University · College of Computing and Data Science, Nanyang Technological University
Watermarking LLM Agent Trajectories
Feb 21, 2026Wenlong Meng, Chen Gong, Terry Yue Zhuo +6LLM Watermarking LLM Agent Security
Zhejiang University, China · University of Virginia, USA · Alibaba Qwen, China +1
Towards Anytime-Valid Statistical Watermarking
Feb 19, 2026Baihe Huang, Eric Xu, Kannan Ramchandran +2LLM Watermarking Anytime-Valid Inference
University of California, Berkeley.
Unforgeable Watermarks for Language Models via Robust Signatures
Feb 17, 2026Huijia Lin, Kameron Shahabi, Min Jae SongLLM Watermarking Robust Watermarking
Paul G. Allen School of Computer Science & Engineering, University of Washington · Data Science Institute, University of Chicago
Protecting Language Models Against Unauthorized Distillation through Trace Rewriting
Feb 16, 2026Xinhang Ma, William Yeoh, Ning Zhang +1LLM Watermarking Knowledge Distillation
Washington University in St. Louis
MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking
Dec 3, 2025Yizhou Zhao, Zhiwei Steven Wu, Adam BlockLLM Watermarking Robust Watermarking
University of Pennsylvania · Carnegie Mellon University · Columbia University
Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation
Oct 20, 2025Asim Mohamed, Martin GubriMultilingual Language Model Evaluation Back-Translation
Parameter Lab · École Polytechnique, IP Paris, CNRS
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
Majority Bit-Aware Watermarking For Large Language Models
Aug 5, 2025Jiahao Xu, Rui Hu, Olivera Kotevska +1Multi-Bit Watermarking Text Watermarking
University of Nevada, Reno · Oak Ridge National Laboratory
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
The Feasibility of Topic-Based Watermarking on Academic Peer Reviews
May 27, 2025Alexander Nemecek, Yuzhou Jiang, Erman AydayText Watermarking LLM Watermarking
Case Western Reserve University
Optimizing watermarks for large language models
Dec 28, 2023Bram WoutersLLM Watermarking Robust Watermarking
University of Amsterdam

Apr 13, 2026J/K move · Enter open · S save

Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models

Shuhao Zhang, Yuli Chen, Jiale Han, Bo Cheng+1

State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications · Hong Kong University of Science and Technology

Adversarial Attacks on LLMs LLM Watermarking Watermark Removal Black-Box Adversarial Attacks

Open paper AskPDF arXiv

Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text. Correspondingly, stealing watermark algorithms (SWAs) derive watermark information from watermarked texts generated by victim LLMs to craft highly targeted adversarial attacks, which compromise the reliability of watermarks. Existing SWAs rely on fixed strategies, overlooking the non-uniform distribution of stolen watermark information and the dynamic nature of real-world LLM generation processes. To address these limitations, we propose Adaptive Stealing (AS), a novel SWA featuring enhanced design flexibility through Position-Based Seal Construction and Adaptive Selection modules. AS operates by defining multiple attack perspectives derived from distinct activation states of contextually ordered tokens. During attack execution, AS dynamically selects the optimal perspective based on watermark compatibility, generation priority, and dynamic generation relevance. Our experiments demonstrate that AS significantly increases steal efficiency against target watermarks under identical experimental conditions. These findings highlight the need for more robust LLM watermarks to withstand potential attacks. We release our code to the community for future research\footnote{https://github.com/DrankXs/AdaptiveStealingWatermark}.