mlsanityData to 14 Oct 2026

Watermarking Text Data on Large Language Models for Dataset Copyright

arXiv 2305.13257 ↗First posted 22 May 2023cs.CRcited by 27

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also vulnerable to various privacy attacks, while much sensitive information exists in the training dataset. The attacker can easily steal sensitive information from public models, e.g., individuals' email addresses and phone numbers. In an attempt to address these issues, particularly the unauthorized use of private data, we introduce a novel watermarking technique via a backdoor-based membership inference approach named TextMarker, which can safeguard diverse forms of private information embedded in the training text data. Specifically, TextMarker only requires data owners to mark a small number of samples for data copyright protection under the black-box access assumption to the target model. Through extensive evaluation, we demonstrate the effectiveness of TextMarker on various real-world datasets, e.g., marking only 0.1% of the training dataset is practically sufficient for effective membership inference with negligible effect on model utility. We also discuss potential countermeasures and show that TextMarker is stealthy enough to bypass them.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 37 of its 52 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

37 of 52 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023A Watermark for Large Language Models24 Jan

Other references · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  6. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
  7. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  8. 2023Augmented Language Models: a Surveycited by 403
  9. 2023A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPTcited by 368
  10. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  11. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
  12. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
24 more
  1. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 224
  2. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 222
  3. 2020BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvementscited by 211
  4. 2020Information Leakage in Embedding Modelscited by 203
  5. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attackscited by 175
  6. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  7. 2021Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoningcited by 113
  8. 2021Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitutioncited by 89
  9. 2023BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPTcited by 76
  10. 2021EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learningcited by 73
  11. 2019Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?cited by 71
  12. 2021Triggerless Backdoor Attack for NLP Tasks with Clean Labelscited by 66
  13. 2022Black-box Dataset Ownership Verification via Backdoor Watermarkingcited by 65
  14. 2022BITE: Textual Backdoor Attacks with Iterative Trigger Injectioncited by 53
  15. 2021Membership Inference Attack Susceptibility of Clinical Language Modelscited by 52
  16. 2019Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentationcited by 32
  17. 2018MLCapsule: Guarded Offline Deployment of Machine Learning as a Servicecited by 31
  18. 2021Privacy Regularization: Joint Privacy-Utility Optimization in Language Modelscited by 30
  19. 2022Membership Inference via Backdooringcited by 27
  20. 2020Natural Backdoor Attack on Text Datacited by 22
  21. 2021BFClass: A Backdoor-free Text Classification Frameworkcited by 19
  22. 2022Leveraging Adversarial Examples to Quantify Membership Information Leakagecited by 19
  23. 2022Privacy Leakage in Text Classification: A Data Extraction Approachcited by 10
  24. 2021Defending Medical Image Diagnostics against Privacy Attacks using Generative Methodscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 12; 2025: 8; 2026: 2.

27 papers.

Sort:

By area:

  1. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  2. 2023A Survey of Text Watermarking in the Era of Large Language Modelscited by 112
  3. 2023Artificial General Intelligence for Medical Imaging Analysiscited by 32
  4. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  5. 2024Watermarking Techniques for Large Language Models: A Surveycited by 23
  6. 2024Double-I Watermark: Protecting Model Copyright for LLM Fine-tuningcited by 21
  7. 2024SoK: Dataset Copyright Auditing in Machine Learning Systemscited by 15
  8. 2025Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMscited by 12
  9. 2023Source Attribution for Large Language Model-Generated Datacited by 11
  10. 2023Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injectioncited by 10
  11. 2025In-Context Watermarks for Large Language Modelscited by 10
  12. 2024Watermark under Fire: A Robustness Evaluation of LLM Watermarkingcited by 9
15 more
  1. 2024Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Modelscited by 8
  2. 2024Watermarking Language Models through Language Modelscited by 8
  3. 2025STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasingscited by 8
  4. 2025Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoptioncited by 7
  5. 2024Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyondcited by 5
  6. 2024Lost in Overlap: Exploring Logit-based Watermark Collision in LLMscited by 4
  7. 2025Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Techniquecited by 4
  8. 2024From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Modelscited by 3
  9. 2024Proactive Schemes: A Survey of Adversarial Attacks for Social Goodcited by 2
  10. 2024Identifying the Source of Generation for Large Language Modelscited by 1
  11. 2025LLM-Text Watermarking based on Lagrange Interpolationcited by 1
  12. 2025LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Datacited by 1
  13. 2026Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implicationscited by 1
  14. 2025Protecting Creative Writing Copyright against AI Imitation via Implicit Watermarkingcited by 0
  15. 2026Synchronization-Free Algebraic Fingerprints for Large Language Models: From Autoregressive to Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
  2. 2026Watermarking for Proprietary Dataset Protection
  3. 2025Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
  4. 2023Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark
  5. 2025Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge
  6. 2026Dataset Watermarking with Provable Black-Box Detection
  7. 2022Distillation-Resistant Watermarking for Model Protection in NLP
  8. 2024Provably Robust Watermarks for Open-Source Language Models