EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Watermarking for Large Language Models: A Survey

Zhiguang Yang, Gejian Zhao, Hanzhou Wu

Mathematics · 26.04.2025 · 13 (9) · 1420

DOI: 10.3390/math13091420 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 26.04.2025. Verfasst von Zhiguang Yang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 105 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Commission of Shanghai Municipality (STCSM), National Natural Science Foundation of China (NSFC), 2024 Xizang Autonomous Region Central Guided Local Science and Technology Development Fund Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid advancement and widespread deployment of large language models (LLMs), concerns regarding content provenance, intellectual property protection, and security threats have become increasingly prominent. Watermarking techniques have emerged as a promising solution for embedding verifiable signals into model outputs, enabling attribution, authentication, and mitigation of unauthorized usage. Despite growing interest in watermarking LLMs, the field lacks a systematic review to consolidate existing research and assess the effectiveness of different techniques. Key challenges include the absence of a unified taxonomy and limited understanding of trade-offs between capacity, robustness, and imperceptibility in real-world scenarios. This paper addresses these gaps by providing a comprehensive survey of watermarking methods tailored to LLMs, structured around three core contributions: (1) We classify these methods as training-free and training-based approaches and detail their mechanisms, strengths, and limitations to establish a structured understanding of existing techniques. (2) We evaluate these techniques based on key criteria—including robustness, imperceptibility, and payload capacity—to identify their effectiveness and limitations, highlighting challenges in designing resilient and practical watermarking solutions. (3) We also discuss critical open challenges while outlining future research directions and practical considerations to drive innovation in watermarking for LLMs. By providing a structured synthesis, this work advances the development of secure and effective watermarking solutions for LLMs.

Förderung

  • Science and Technology Commission of Shanghai Municipality (STCSM)
  • National Natural Science Foundation of China (NSFC)
  • 2024 Xizang Autonomous Region Central Guided Local Science and Technology Development Fund Project
  • Basic Research Program for Natural Science of Guizhou Province

Zitieren

APA

Yang, Z., Zhao, G., & Wu, H. (2025). Watermarking for Large Language Models: A Survey. Mathematics, 13(9), 1420. https://doi.org/10.3390/math13091420

Vancouver

Yang Z, Zhao G, Wu H. Watermarking for Large Language Models: A Survey. Mathematics. 2025;13(9):1420. doi:10.3390/math13091420

BibTeX
@article{Yang2025,
  author = {Yang, Zhiguang and Zhao, Gejian and Wu, Hanzhou},
  title = {Watermarking for Large Language Models: A Survey},
  journal = {Mathematics},
  year = {2025},
  volume = {13},
  number = {9},
  pages = {1420},
  doi = {10.3390/math13091420}
}
Kostenlos starten →