Natural language watermarking via morphosyntactic alterations
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Several techniques like paraphrasing can fool AI detectors.
“Due to this, several techniques like paraphrasing can fool the AI detectors [95].”
From Survey on Plagiarism Detection in Large Language Models: The Impact of ChatGPT and Gemini on Academic Integrity (2024) · cites this paper as [95]
Cites
Topkara, M., Taskiran, C. M., & Delp III, E. J. (2005) · SPIE Proceedings · doi:10.1117/12.593790 · Cited by 63 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats
Mubarak, R., Alsboui, T., Alshaikh, O., Inuwa-Dutse, I., Khan, S., & Parkinson, S. (2023) · IEEE Access · doi:10.1109/access.2023.3344653 · Cited by 132 · see citing works
A Watermark for Large Language Models
Kirchenbauer, J., Geiping, J., Wen, Y., Katz, J., Miers, I., & Goldstein, T. (2023) · arXiv · doi:10.48550/arxiv.2301.10226 · Cited by 194 · see citing works
“Rule-based watermarks were further improved in a series of works (Chiang et al., 2004; Topkara et al., 2006a;b; Meral et al., 2009) with variants also embedding watermarks based on synonym tables instead of only parse trees.”
MAGE: Machine-generated Text Detection in the Wild
Li, Y., Li, Q., Cui, L., Bi, W., Wang, Z., Wang, L., Yang, L., Shi, S., & Zhang, Y. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.3 · Cited by 79 · see citing works
On the Possibilities of AI-Generated Text Detection
Chakraborty, S., Bedi, A. S., Zhu, S., An, B., Manocha, D., & Huang, F. (2023) · arXiv · doi:10.48550/arxiv.2304.04736 · Cited by 59 · see citing works
Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges
Huang, B., Chen, C., & Shu, K. (2025) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3715073.3715076 · Cited by 42 · see citing works
“(Kirchenbauer et al., 2023, Meral et al., 2009, Topkara et al., 2005, Zhao et al., 2023).”
Pudasaini, S., Miralles-Pechuán, L., Lillis, D., & Salvador, M. L. (2024) · arXiv · doi:10.48550/arxiv.2407.13105 · Cited by 8 · see citing works
“Techniques like morphosyntactic alterations and synonym substitution were used for watermarking natural language [97, 98].”
Method
- Authors
- Meral, H. M., Sankur, B., Sumru Özsoy, A., Güngör, T., & Sevinç, E.
- Affiliations
- Boğaziçi University (TR)
- Corresponding author
- Güngör, Tunga
- Venue
- Computer Speech & Language
- Publisher
- Elsevier BV
- Published
- 2009-01
- Volume
- 23
- Issue
- 1
- Pages
- 107-125
- ISSN
- 0885-2308 (ISSN-L)
- OpenAlex
- W1975586457
- Cited by
- 113
- References
- 1
- Citations by year
- 2026: 5 · 2025: 11 · 2024: 5 · 2023: 6 · 2022: 8 · 2021: 4 · 2020: 2 · 2019: 4 · 2018: 8 · 2017: 5 · 2016: 9 · 2015: 5 · 2014: 6 · 2013: 3 · 2012: 10
- FWCI
- 10.54
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Computer Speech & Language (publishedVersion)
- Funders
- Engineering and Physical Sciences Research Council (EP/F028938/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Hardware and Architecture › Physical Unclonable Functions (PUFs) and Hardware Security
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- WordNet, semantic preservation, imperceptibility, edit distance, agglutinative languages, Turkish language, free word order
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
