mlsanityData to 7 Oct 2026

Watermarking LLMs with Weight Quantization

arXiv 2310.11237 ↗First posted 17 Oct 2023cs.CLcited by 19

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

Abstract (arXiv)

Abuse of large language models reveals high risks as large language models are being deployed at an astonishing speed. It is important to protect the model weights to avoid malicious usage that violates licenses of open-source large language models. This paper proposes a novel watermarking strategy that plants watermarks in the quantization process of large language models without pre-defined triggers during inference. The watermark works when the model is used in the fp32 mode and remains hidden when the model is quantized to int8, in this way, the users can only inference the model without further supervised fine-tuning of the model. We successfully plant the watermark into open-source large language model weights including GPT-Neo and LLaMA. We hope our proposed method can provide a potential direction for protecting model weights in the era of large language model applications.

Key facts. Cited by 19 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 24 of its 29 references that are in the map. First posted on arXiv 17 Oct 2023.

Builds on

24 of 29 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023A Watermark for Large Language Models24 Jan
  2. 2022CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks19 Sep
  3. 2021Protecting Intellectual Property of Language Generation APIs with Lexical Watermark5 Dec

Other references · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  6. 2018Hierarchical Neural Story Generationcited by 1,182
  7. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  8. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  9. 2019Defending Against Neural Fake Newscited by 553
  10. 2019Q-BERT: Hessian Based Ultra Low Precision Quantization of BERTcited by 355
  11. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 318
  12. 2019Q8BERT: Quantized 8Bit BERTcited by 296
9 more
  1. 2021Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoningcited by 103
  2. 2019Real or Fake? Learning to Discriminate Machine from Human Generated Textcited by 98
  3. 2019Neural Linguistic Steganographycited by 73
  4. 2020A Statistical Framework for Low-bitwidth Training of Deep Neural Networkscited by 51
  5. 2021Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attackscited by 44
  6. 2017Generating Steganographic Text with LSTMscited by 41
  7. 2023Origin Tracing and Detecting of LLMscited by 39
  8. 2020Towards Fully 8-bit Integer Inference for the Transformer Modelcited by 35
  9. 2019Towards Near-imperceptible Steganographic Textcited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 9; 2025: 6; 2026: 3.

19 papers.

Sort:

By area:

  1. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 247
  2. 2024A Survey of Recent Backdoor Attacks and Defenses in Large Language Modelscited by 36
  3. 2023Optimizing watermarks for large language modelscited by 22
  4. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  5. 2024Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Mergingcited by 17
  6. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarkingcited by 14
  7. 2024EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Modelscited by 11
  8. 2024Watermarking Language Models through Language Modelscited by 7
  9. 2025Model Unmerging: Making Your Models Unmergeable for Secure Model Sharingcited by 6
  10. 2025BitMark: Watermarking Bitwise Autoregressive Image Generative Modelscited by 5
  11. 2024Watermarking Large Language Models and the Generated Content: Opportunities and Challengescited by 2
  12. 2025SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprintingcited by 2
7 more
  1. 2024Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarkingcited by 0
  2. 2024Signal Watermark on Large Language Modelscited by 0
  3. 2025WaterDrum: Watermarking for Data-centric Unlearning Metriccited by 0
  4. 2025Watermarking Large Language Models in Europe: Interpreting the AI Act in Light of Technologycited by 0
  5. 2026Provable Model Provenance Set for Large Language Modelscited by 0
  6. 2026Functional Subspace Watermarking for Large Language Modelscited by 0
  7. 2026Stemma: Induced Decision Regions Reveal LLM Provenancecited by 0