mlsanityData to 7 Oct 2026

Publicly-Detectable Watermarking for Language Models

arXiv 2310.18491 ↗First posted 27 Oct 2023cs.LG cs.CL cs.CRcited by 69

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

Abstract (arXiv)

We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone. We embed a publicly-verifiable cryptographic signature into LM output using rejection sampling and prove that this produces unforgeable and distortion-free (i.e., undetectable without access to the public key) text output. We make use of error-correction to overcome periods of low entropy, a barrier for all prior watermarking schemes. We implement our scheme and find that our formal claims are met in practice.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 22 of its 59 references that are in the map. First posted on arXiv 27 Oct 2023.

Builds on

22 of 59 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Robust Distortion-free Watermarks for Language Models28 Jul
  2. 2023Undetectable Watermarks for Language Models25 May
  3. 2023DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated Text9 May
  4. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense23 Mar
  5. 2023Can AI-Generated Text be Reliably Detected?17 Mar
  6. 2023A Watermark for Large Language Models24 Jan

Other references · 16

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  7. 2023Mistral 7Bcited by 3,065
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  10. 2019Defending Against Neural Fake Newscited by 553
  11. 2019GLTR: Statistical Detection and Visualization of Generated Textcited by 490
  12. 2019Neural Text Generation with Unlikelihood Trainingcited by 489
4 more
  1. 2020Automatic Detection of Machine Generated Text: A Critical Surveycited by 160
  2. 2020Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hidingcited by 121
  3. 2023On the Possibilities of AI-Generated Text Detectioncited by 88
  4. 2014Deletion codes in the high-noise and high-rate regimescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 28; 2025: 18; 2026: 18.

69 papers.

Sort:

By area:

  1. 2023A Survey of Text Watermarking in the Era of Large Language Modelscited by 102
  2. 2024MarkLLM: An Open-Source Toolkit for LLM Watermarkingcited by 80
  3. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Modelscited by 77
  4. 2023On the Learnability of Watermarks for Language Modelscited by 72
  5. 2023Mark My Words: Analyzing and Evaluating Language Model Watermarkscited by 62
  6. 2024An Entropy-based Text Watermarking Detection Methodcited by 61
  7. 2024Adaptive Text Watermark for Large Language Modelscited by 60
  8. 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-offcited by 48
  9. 2024No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choicescited by 47
  10. 2024SoK: Watermarking for AI-Generated Contentcited by 43
  11. 2024Pseudorandom Error-Correcting Codescited by 40
  12. 2024GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trickcited by 31
38 more
  1. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29
  2. 2023Towards Optimal Statistical Watermarkingcited by 25
  3. 2024Black-Box Detection of Language Model Watermarkscited by 22
  4. 2024Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signaturecited by 21
  5. 2024Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)cited by 20
  6. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  7. 2024Learning to Watermark LLM-generated Text via Reinforcement Learningcited by 19
  8. 2025BiMark: Unbiased Multilayer Watermarking for Large Language Modelscited by 18
  9. 2024Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approachcited by 17
  10. 2024Watermarking Language Models for Many Adaptive Userscited by 16
  11. 2024Large Language Model Watermark Stealing With Mixed Integer Programmingcited by 13
  12. 2024Edit Distance Robust Watermarks via Indexing Pseudorandom Codescited by 12
  13. 2024Provably Robust Watermarks for Open-Source Language Modelscited by 12
  14. 2025On the Difficulty of Constructing a Robust and Publicly-Detectable Watermarkcited by 9
  15. 2025Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attackscited by 8
  16. 2024Is The Watermarking Of LLM-Generated Code Robust?cited by 7
  17. 2024Watermark under Fire: A Robustness Evaluation of LLM Watermarkingcited by 7
  18. 2025Verifying LLM Inference to Detect Model Weight Exfiltrationcited by 6
  19. 2026Antidistillation Fingerprintingcited by 6
  20. 2025Watermarking Discrete Diffusion Language Modelscited by 5
  21. 2024On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attackscited by 4
  22. 2024Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyondcited by 4
  23. 2024Securing the Future of GenAI: Policy and Technologycited by 4
  24. 2024Discovering Spoofing Attempts on Language Model Watermarkscited by 4
  25. 2025Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Modelscited by 4
  26. 2025A Survey of LLM × DATAcited by 4
  27. 2025SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstructioncited by 4
  28. 2025Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigmcited by 4
  29. 2024From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Modelscited by 3
  30. 2024Multi-Designated Detector Watermarking for Language Modelscited by 3
  31. 2024Large Language Models as Carriers of Hidden Messagescited by 2
  32. 2025SoK: Are Watermarks in LLMs Ready for Deployment?cited by 2
  33. 2025GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectorscited by 2
  34. 2026MC2Mark: Distortion-Free Multi-Bit Watermarking for Long Messagescited by 2
  35. 2025HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictionscited by 1
  36. 2025The Coding Limits of Robust Watermarking for Generative Modelscited by 1
  37. 2025PVMark: Enabling Public Verifiability for LLM Watermarking Schemescited by 1
  38. 2025Ideal Attribution and Faithful Watermarks for Language Modelscited by 1

50 most cited of 69 All 69 (JSON)