mlsanityData to 7 Oct 2026

EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models

arXiv 2402.17938 ↗First posted 27 Feb 2024cs.CR cs.CLcited by 11

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

Abstract (arXiv)

This paper introduces EmMark,a novel watermarking framework for protecting the intellectual property (IP) of embedded large language models deployed on resource-constrained edge devices. To address the IP theft risks posed by malicious end-users, EmMark enables proprietors to authenticate ownership by querying the watermarked model weights and matching the inserted signatures. EmMark's novelty lies in its strategic watermark weight parameters selection, nsuring robustness and maintaining model quality. Extensive proof-of-concept evaluations of models from OPT and LLaMA-2 families demonstrate EmMark's fidelity, achieving 100% success in watermark extraction with model performance preservation. EmMark also showcased its resilience against watermark removal and forging attacks.

Key facts. Cited by 11 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 11 of its 23 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

11 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Watermarking LLMs with Weight Quantization17 Oct

Other references · 10

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  3. 2016Pointer Sentinel Mixture Modelscited by 2,992
  4. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  5. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  6. 2022Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Modelscited by 176
  7. 2021Primer: Searching for Efficient Transformers for Language Modelingcited by 162
  8. 2022Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protectioncited by 80
  9. 2021From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compressioncited by 18
  10. 2022LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Modelscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 4.

11 papers.

  1. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  2. 2024Watermarking Large Language Models and the Generated Content: Opportunities and Challengescited by 2
  3. 2025SoK: Are Watermarks in LLMs Ready for Deployment?cited by 2
  4. 2025Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applicationscited by 1
  5. 2026Robust LLM Watermarking with Minimal Semantic Distortion for IP Protectioncited by 1
  6. 2024Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarkingcited by 0
  7. 2025Invariant-based Robust Weights Watermark for Large Language Modelscited by 0
  8. 2025Watermarking Large Language Models in Europe: Interpreting the AI Act in Light of Technologycited by 0
  9. 2026Functional Subspace Watermarking for Large Language Modelscited by 0
  10. 2026LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chainscited by 0
  11. 2026LLM Watermarking as Big Data Provenance: A Deployment-Oriented Systematizationcited by 0