[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to main content

Temperature-Based Watermarking and Detection for Large Language Models

  • Conference paper
  • First Online:
Algorithms and Architectures for Parallel Processing (ICA3PP 2024)

Abstract

With the wide application of Large Language Models (LLMs), protecting the copyright of generated content and preventing its misuse becomes important. This paper proposes a temperature-based watermark embedding algorithm that embeds watermarks in text using the Softmax function and polynomial sampling techniques. Meanwhile, this paper also discusses a watermark detection technique based on statistical testing, which can effectively identify and verify watermarks embedded in text. By applying these techniques to different LLMs and computing environments, including OPT series, Llama series, BLOOM series and GPT-2, this paper analyses the scenarios, evaluates the key parameters in the algorithms and proposes solutions to ensure the integration of watermarks without compromising on the performance of the model or the naturalness of the generated text.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
GBP 19.95
Price includes VAT (United Kingdom)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
GBP 49.99
Price includes VAT (United Kingdom)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
GBP 59.99
Price includes VAT (United Kingdom)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bubeck, S., et al.: Sparks of artificial general intelligence: early experiments with GPT-4. arXiv preprint arXiv:2303.12712 (2023)

  2. Turing, A.M.: Computing Machinery and Intelligence. Springer (2009)

    Google Scholar 

  3. Thede, S.M., Harper, M.: A second-order hidden Markov model for part-of-speech tagging. In: Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, pp. 175–182 (1999)

    Google Scholar 

  4. Bahl, L.R., Brown, P.F., De Souza, P.V., Mercer, R.L.: A tree-based statistical language model for natural language speech recognition. IEEE Trans. Acoust. Speech Signal Process. 37(7), 1001–1008 (1989)

    Article  MATH  Google Scholar 

  5. Brants, T., Popat, A., Xu, P., Och, F.J., Dean, J.: Large language models in machine translation. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 858–867 (2007)

    Google Scholar 

  6. Liu, X., Croft, W.B.: Statistical language modeling for information retrieval. Annu. Rev. Inf. Sci. Technol. 39(1), 1–31 (2005)

    Article  MATH  Google Scholar 

  7. Mikolov, T., et al.: Statistical language models based on neural networks. Presentation at Google, Mountain View, 2 April 2012, vol. 80, no. 26 (2012)

    Google Scholar 

  8. Mirsky, Y., et al.: The threat of offensive AI to organizations. Comput. Secur. 124, 103006 (2023)

    Article  MATH  Google Scholar 

  9. Bergman, A.S., et al.: Guiding the release of safer e2e conversational AI through value sensitive design. In: Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics (2022)

    Google Scholar 

  10. Megías, D., Kuribayashi, M., Rosales, A., Mazurczyk, W.: Dissimilar: towards fake news detection using information hiding, signal processing and machine learning. In: Proceedings of the 16th International Conference on Availability, Reliability and Security, pp. 1–9 (2021)

    Google Scholar 

  11. Tang, R., Feng, Q., Liu, N., Yang, F., Hu, X.: Did you train on my dataset? Towards public dataset protection with cleanlabel backdoor watermarking. ACM SIGKDD Explor. Newsl. 25(1), 43–53 (2023)

    Article  Google Scholar 

  12. Zhao, X., Wang, Y.-X., Li, L.: Protecting language generation models via invisible watermarking. In: International Conference on Machine Learning. PMLR, pp. 42187–42199 (2023)

    Google Scholar 

  13. Brassil, J.T., Low, S., Maxemchuk, N.F., O’Gorman, L.: Electronic marking and identification techniques to discourage document copying. IEEE J. Sel. Areas Commun. 13(8), 1495–1504 (1995)

    Article  MATH  Google Scholar 

  14. Begum, M., Uddin, M.S.: Digital image watermarking techniques: a review. Information 11(2), 110 (2020)

    Article  MATH  Google Scholar 

  15. Por, L.Y., Wong, K., Chee, K.O.: UniSpaCh: a text-based data hiding method using Unicode space characters. J. Syst. Softw. 85(5), 1075–1082 (2012)

    Article  Google Scholar 

  16. Rizzo, S.G., Bertini, F., Montesi, D.: Content-preserving text watermarking through Unicode homoglyph substitution. In: Proceedings of the 20th International Database Engineering & Applications Symposium, pp. 97–104 (2016)

    Google Scholar 

  17. Sato, R., Takezawa, Y., Bao, H., Niwa, K., Yamada, M.: Embarrassingly simple text watermarks. arXiv preprint arXiv:2310.08920 (2023)

  18. Munyer, T., Zhong, X.: DeepTextMark: deep learning based text watermarking for detection of large language model generated text. arXiv preprint arXiv:2305.05773 (2023)

  19. Topkara, U., Topkara, M., Atallah, M.J.: The hiding virtues of ambiguity: quantifiably resilient watermarking of natural language text through synonym substitutions. In: Proceedings of the 8th Workshop on Multimedia and Security, pp. 164–174 (2006)

    Google Scholar 

  20. Fellbaum, C.: WordNet: An Electronic Lexical Database. MIT Press, Cambridge (1998)

    Book  MATH  Google Scholar 

  21. Yang, X., et al.: Tracing text provenance via context-aware lexical substitution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 10, pp. 11613–11621 (2022)

    Google Scholar 

  22. Yoo, K., Ahn, W., Jang, J., Kwak, N.: Robust multi-bit natural language watermarking through invariant features. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2092–2115 (2023)

    Google Scholar 

  23. Topkara, M., Topkara, U., Atallah, M.J.: Words are not enough: sentence level natural language watermarking. In: Proceedings of the 4th ACM International Workshop on Contents Protection and Security, pp. 37–46 (2006)

    Google Scholar 

  24. Abdelnabi, S., Fritz, M.: Adversarial watermarking transformer: towards tracing text provenance with data hiding. In: 2021 IEEE Symposium on Security and Privacy (SP), pp. 121–140. IEEE (2021)

    Google Scholar 

  25. Zhang, R., Hussain, S.S., Neekhara, P., Koushanfar, F.: Remark-LLM: a robust and efficient watermarking framework for generative large language models. arXiv preprint arXiv:2310.12362 (2023)

  26. Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)

  27. Liu, Y., Hu, H., Zhang, X., Sun, L.: Watermarking text data on large language models for dataset copyright protection. arXiv preprint arXiv:2305.13257 (2023)

  28. Sun, Z., Du, X., Song, F., Ni, M., Li, L.: CoProtector: protect open-source code against unauthorized training usage with data poisoning. In: Proceedings of the ACM Web Conference 2022, pp. 652–660 (2022)

    Google Scholar 

  29. Kirchenbauer, J., Geiping, J., Wen, Y., Katz, J., Miers, I., Goldstein, T.: A watermark for large language models. In: International Conference on Machine Learning. PMLR, pp. 17061–17084 (2023)

    Google Scholar 

  30. Iqbal, M.M., Khadam, U., Han, K.J., Han, J., Jabbar, S.: A robust digital watermarking algorithm for text document copyright protection based on feature coding. In: 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), pp. 1940–1945. IEEE (2019)

    Google Scholar 

Download references

Acknowledgments

This work was supported by the National Natural Science Foundation of China (No. U23A20307, No. 62272118). We extend our gratitude to the Foundation for their financial support, our collaborators and team members for their contributions, and the editors and reviewers for their valuable feedback.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Pei-Gen Ye .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chen, W., Zhang, Z., Ren, H., Ye, PG., Li, Z., Huang, S. (2025). Temperature-Based Watermarking and Detection for Large Language Models. In: Zhu, T., Li, J., Castiglione, A. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2024. Lecture Notes in Computer Science, vol 15251. Springer, Singapore. https://doi.org/10.1007/978-981-96-1525-4_18

Download citation

  • DOI: https://doi.org/10.1007/978-981-96-1525-4_18

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-96-1524-7

  • Online ISBN: 978-981-96-1525-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics