Skip to main content
Springer Nature Link
Log in

Robust and semantic-faithful post-hoc watermarking of text generated by black-box language models

  • Letter
  • Published:
Frontiers of Computer Science Aims and scope Submit manuscript

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

References

  1. Stokel-Walker C. ChatGPT listed as author on research papers: many scientists disapprove. Nature, 2023, 613(7945): 620–621

    Article  Google Scholar 

  2. Liebrenz M, Schleifer R, Buadze A, Bhugra D, Smith A. Generating scholarly content with ChatGPT: ethical challenges for medical publishing. The Lancet Digital Health, 2023, 5(3): e105–e106

    Article  Google Scholar 

  3. Qiang J, Zhu S, Li Y, Zhu Y, Yuan Y, Wu X. Natural language watermarking via paraphraser-based lexical substitution. Artificial Intelligence, 2023, 317: 103859

    Article  MATH  Google Scholar 

  4. Mitchell E, Lee Y, Khazatsky A, Manning C D, Finn C. DetectGPT: zero-shot machine-generated text detection using probability curvature. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 24950–24962

    Google Scholar 

  5. Kirchenbauer J, Geiping J, Wen Y, Katz J, Miers I, Goldstein T. A watermark for large language models. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 17061–17084

    Google Scholar 

  6. Yang X, Chen K, Zhang W, Liu C, Qi Y, Zhang J, Fang H, Yu N. Watermarking text generated by black-box language models. 2023, arXiv preprint arXiv: 2305.08883

    MATH  Google Scholar 

  7. 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. 2023, 2092–2115

    MATH  Google Scholar 

  8. Campos R, Mangaravite V, Pasquali A, Jorge A M, Nunes C, Jatowt A. YAKE! Collection-independent automatic keyword extractor. In: Proceedings of the 40th European Conference on IR Research Advances in Information Retrieval. 2018, 806–810

    Google Scholar 

  9. Qiang J, Liu K, Li Y, Yuan Y, Zhu Y. ParaLS. Lexical substitution via pretrained paraphraser. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023, 3731–3746

    MATH  Google Scholar 

Download references

Acknowledgements

This research was partially supported by the National Natural Science Foundation of China (Grant Nos. 62076217, U21B2048 and U22B2037), the National Language Commission (ZDI145-71), the Blue Project of Jiangsu, the Top-level Talents Support Program, the Blue Project and Teaching Reform Project (YZUJX2023-D8) of Yangzhou University.

Author information

Authors and Affiliations

  1. School of Information Engineering, Yangzhou University, Yangzhou, 225127, China

    Jifei Hao, Jipeng Qiang, Yi Zhu, Yun Li & Yunhao Yuan

  2. China Academy of Electronic and Information Technology, Beijing, 100041, China

    Xiaocheng Hu & Xiaoye Ouyang

Authors
  1. Jifei Hao
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jipeng Qiang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yi Zhu
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yun Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Yunhao Yuan
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Xiaocheng Hu
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Xiaoye Ouyang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Jipeng Qiang.

Ethics declarations

Competing interests The authors declare that they have no competing interests or financial conflicts to disclose.

Electronic Supplementary Material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hao, J., Qiang, J., Zhu, Y. et al. Robust and semantic-faithful post-hoc watermarking of text generated by black-box language models. Front. Comput. Sci. 19, 199357 (2025). https://doi.org/10.1007/s11704-024-40751-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11704-024-40751-w