Natural language watermarking
Abstract
In this paper we discuss natural language watermarking, which uses the structure of the sentence constituents in natural language text in order to insert a watermark. This approach is different from techniques, collectively referred to as "text watermarking," which embed information by modifying the appearance of text elements, such as lines, words, or characters. We provide a survey of the current state of the art in natural language watermarking and introduce terminology, techniques, and tools for text processing. We also examine the parallels and differences of the two watermarking domains and outline how techniques from the image watermarking domain may be applicable to the natural language watermarking domain.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Still being checked.
Cited by
Sorted by citations
The hiding virtues of ambiguity
Topkara, U., Topkara, M., & Atallah, M. J. (2006) · ACM workshop on Multimedia and security · doi:10.1145/1161366.1161397 · Cited by 152 · see citing works
Self-citationLiu, T.-Y., & Tsai, W. (2007) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2006.890310 · Cited by 141 · see citing works
UniSpaCh: A text-based data hiding method using Unicode space characters
Por, L. Y., Wong, K., & Chee, K. O. (2011) · Journal of Systems and Software · doi:10.1016/j.jss.2011.12.023 · Cited by 134 · see citing works
A Review of Text Watermarking: Theory, Methods, and Applications
Kamaruddin, N. S., Kamsin, A., Por, L. Y., & Rahman, H. (2018) · IEEE Access · doi:10.1109/access.2018.2796585 · Cited by 119 · see citing works
Natural language watermarking via morphosyntactic alterations
Meral, H. M., Sankur, B., Sumru Özsoy, A., Güngör, T., & Sevinç, E. (2009) · Computer Speech & Language · doi:10.1016/j.csl.2008.04.001 · Cited by 113 · see citing works
Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
Abdelnabi, S., & Fritz, M. (2021) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp40001.2021.00083 · Cited by 105 · see citing works
Chang, C.-Y., & Clark, S. C. (2013) · Computational Linguistics · doi:10.1162/coli_a_00176 · Cited by 87 · see citing works
A Review of Digital Watermarking Techniques for Text Documents
Jalil, Z., & Mirza, A. M. (2009) · International Conference on Information and Multimedia Technology · doi:10.1109/icimt.2009.11 · Cited by 81 · see citing works
Topkara, M., Topkara, U., & Atallah, M. J. (2006) · doi:10.1145/1178766.1178777 · Cited by 72 · see citing works
Self-citationContent-preserving Text Watermarking through Unicode Homoglyph Substitution
Rizzo, S., Bertini, F., & Montesi, D. (2016) · International Database Engineering and Applications Symposium (IDEAS) · doi:10.1145/2938503.2938510 · Cited by 47 · see citing works
Robust Multi-bit Natural Language Watermarking through Invariant Features
Yoo, K., Ahn, W., Jang, J., & Kwak, N. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.117 · Cited by 43 · see citing works
Watermarking geographical data on spatial topological relations
Wang, C., Peng, Z., Peng, Y., Liang, Y., Wang, J., & Zhao, Q. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0536-9 · Cited by 41 · see citing works
Natural language watermarking via paraphraser-based lexical substitution
Qiang, J., Zhu, S., Li, Y., Zhu, Y. Q., Yuan, Y., & Wu, X. (2023) · Artificial Intelligence · doi:10.1016/j.artint.2023.103859 · Cited by 39 · see citing works
An Efficient Linguistic Steganography for Chinese Text
Liu, Y., Sun, X., Can, G., & Hong, W. (2007) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2007.4285095 · Cited by 39 · 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).”
Tamper-proofing of electronic and printed text documents via robust hashing and data-hiding
Villan, R., Voloshynovskiy, S., Koval, O., Deguillaume, F., & Pun, T. (2007) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.704097 · Cited by 36 · see citing works
A Coverless Plain Text Steganography Based on Character Features
Wang, K., & Gao, Q. (2019) · IEEE Access · doi:10.1109/access.2019.2929123 · Cited by 32 · see citing works
Word length based zero-watermarking algorithm for tamper detection in text documents
Jalil, Z., Mirza, A. M., & Jabeen, H. (2010) · International Conference on Computer Engineering and Technology · doi:10.1109/iccet.2010.5486185 · Cited by 32 · see citing works
A zero-watermarking algorithm for text documents based on structural components
Jalil, Z., Mirza, A. M., & Iqbal, T. (2010) · International Conference on Information and Emerging Technologies · doi:10.1109/iciet.2010.5625705 · Cited by 29 · see citing works
Recognition in software watermarking
Zhu, W., & Thomborson, C. D. (2006) · doi:10.1145/1178766.1178776 · Cited by 27 · see citing works
Deng, C., Duan, Y., Jin, X., Chang, H., Tian, Y., Liu, H., Wang, Y., Gao, K., Zou, H. P., Jin, Y., et al. (2025) · AI and Ethics · doi:10.1007/s43681-025-00797-3 · Cited by 49 · see citing works
Information Hiding in Text Using Typesetting Tools with Stego-Encoding
Chen, C., Shuozhong, W., & Xinpeng, Z. (2006) · International Conference on Innovative Computing, Information and Control · doi:10.1109/icicic.2006.101 · Cited by 23 · see citing works
An Invisible Text Watermarking Algorithm using Image Watermark
Jalil, Z., & Mirza, A. M. (2010) · Springer eBooks · doi:10.1007/978-90-481-9112-3_25 · Cited by 21 · see citing works
An Optimized Natural Language Watermarking Algorithm based on TMR
Peng, L., Lu, Z., Zhou, Z., & Gu, J. (2008) · International Conference for Young Computer Scientists · doi:10.1109/icycs.2008.398 · Cited by 21 · see citing works
Content-Aware Steganography: About Lazy Prisoners and Narrow-Minded Wardens
Bergmair, R., & Katzenbeisser, S. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74124-4_8 · Cited by 20 · see citing works
A zero text watermarking algorithm based on non-vowel ASCII characters
Jalil, Z., Aziz, H., Shahid, S. B., Arif, M., & Mirza, A. M. (2010) · International Conference on Educational and Information Technology · doi:10.1109/iceit.2010.5607625 · Cited by 19 · see citing works
Natural Language Watermarking Based on Syntactic Displacement and Morphological Division
Kim, M.-Y., Zai͏̈ane, O. R., & Goebel, R. G. (2010) · IEEE Annual Computer Software and Applications Conference Workshops (COMPSACW) · doi:10.1109/compsacw.2010.37 · Cited by 18 · see citing works
Yang, Z., Feng, Z., Huo, R., Lin, H., Zheng, H., Nie, R., & Chen, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126694 · Cited by 17 · see citing works
Text watermarking algorithm based on semantic role labeling
Chen, J., Yang, F., Ma, H., & Lu, Q. (2016) · International Conference on Digital Information Processing, Data Mining, and Wireless Communications (DIPDMWC) · doi:10.1109/dipdmwc.2016.7529374 · Cited by 15 · see citing works
Steganography via running short text messages
Samphaiboon, N. (2009) · Multimedia Tools and Applications · doi:10.1007/s11042-009-0432-3 · Cited by 14 · see citing works
Natural Language Watermarking Using Chinese Syntactic Transformations
Wang, H., Sun, X., Liu, Y., & Liu, Y. (2008) · Information Technology Journal · doi:10.3923/itj.2008.904.910 · Cited by 14 · see citing works
Text Watermarking Using Combined Image-plus-Text Watermark
Jalil, Z., & Mirza, A. M. (2010) · International Workshop on Education Technology and Computer Science · doi:10.1109/etcs.2010.494 · Cited by 14 · see citing works
Text Authorship Verification through Watermarking
Rizzo, S., Bertini, F., & Montesi, D. (2016) · European Intelligence and Security Informatics Conference · doi:10.1109/eisic.2016.043 · Cited by 13 · see citing works
Natural language watermarking for german texts
Halvani, O., Steinebach, M., Wolf, P., & Zimmermann, R. (2013) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/2482513.2482522 · Cited by 13 · see citing works
Text Encryption Algorithm Based on Natural Language Processing
Jing, X., Yu, H., Fei, H., & Li, Z. (2012) · International Conference on Multimedia Information Networking and Security · doi:10.1109/mines.2012.216 · Cited by 13 · see citing works
MIMIC-PPT: Mimicking-Based Steganography for Microsoft Power Point Document
Liu, Y., Sun, X., Liu, Y., & Li, C. (2008) · Information Technology Journal · doi:10.3923/itj.2008.654.660 · Cited by 12 · see citing works
Natural Language Watermarking for Korean Using Adverbial Displacement
Kim, M. (2008) · International Conference on Multimedia and Ubiquitous Engineering (MUE) · doi:10.1109/mue.2008.79 · Cited by 10 · see citing works
A Framework Components for Natural Language Steganalysis
Din, R., Samsudin, A., & Lertkrai, P. (2012) · International Journal of Computer Theory and Engineering · doi:10.7763/ijcte.2012.v4.548 · Cited by 10 · see citing works
Text watermarking algorithm using structural approach
Bharati, P. D., & Nitin, P. N. (2012) · World Congress on Information and Communication Technologies · doi:10.1109/wict.2012.6409152 · Cited by 9 · see citing works
A robust zero-watermarking algorithm for copyright protection of text documents
Jalil, Z., & Mirza, A. M. (2012) · Journal of the Chinese Institute of Engineers · doi:10.1080/02533839.2012.734470 · Cited by 9 · see citing works
Hiding Information by Context-Based Synonym Substitution
Zheng, X., Huang, L., Chen, Z., Yu, Z., & Yang, W. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03688-0_16 · Cited by 8 · see citing works
Steganography in social networks
Nechta, I. V. (2017) · Siberian Symposium on Data Science and Engineering (SSDSE) · doi:10.1109/ssdse.2017.8071959 · Cited by 7 · see citing works
Natural Language Watermarking by Morpheme Segmentation
Kim, M. (2009) · Asian Conference on Intelligent Information and Database Systems · doi:10.1109/aciids.2009.21 · Cited by 6 · see citing works
DWTC: A Dual Watermarking Scheme Based on Threshold Cryptography for Web Document
Li, D., & Zhang, B. (2010) · International Conference on Computer Application and System Modeling · doi:10.1109/iccasm.2010.5620633 · Cited by 6 · see citing works
Adaptive‐capacity and robust natural language watermarking for agglutinative languages
Kim, M., & Goebel, R. G. (2011) · Security and Communication Networks · doi:10.1002/sec.336 · Cited by 5 · see citing works
Watermarking Tools for Turkish Texts
Meral, H. M., Sankur, B., & Özsoy, A. S. (2006) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2006.1659827 · Cited by 5 · see citing works
A review of digital watermarking techniques: Current trends, challenges and opportunities
Singh, B., & Kasana, G. (2024) · Web Intelligence · doi:10.3233/web-230280 · Cited by 4 · see citing works
A Hybrid Natural Language Information Hiding System
Lu, H., Gui, X., Rei-Feng, W. U., -, B. X., & Hu, C. (2012) · Elektronika ir Elektrotechnika · doi:10.5755/j01.eee.18.9.2817 · Cited by 3 · see citing works
A watermarking scheme for natural language documents
Gu, J., & Cheng, Y. (2010) · International Conference on Information Management and Engineering (ICIME) · doi:10.1109/icime.2010.5477622 · Cited by 3 · see citing works
Empirical Paraphrasing of Modern Greek Text in Two Phases: An Application to Steganography
Kermanidis, K. L., & Magkos, E. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-00382-0_43 · Cited by 3 · see citing works
Ensuring news integrity against online information disorder through text watermarking and blockchain
Bertini, F., Benetton, A., & Montesi, D. (2025) · Blockchain Research and Applications · doi:10.1016/j.bcra.2025.100414 · Cited by 4 · see citing works
Authorship Proof for Textual Document
Wu, J., & Stinson, D. R. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88961-8_15 · Cited by 2 · see citing works
A Survey on AI-Generated Text Detection: Methods, Challenges, and Future Directions
Ismail, A. A., Ahmed, C., & ElKorany, A. (2025) · Future International Conference on Artificial Intelligence and Cybersecurity (FICAC) · doi:10.1109/ficac65757.2025.11341850 · Cited by 1 · see citing works
Authorship Protection for Textual Documents
Adimoolam, M., Vasanth, I. V. S. S., Prabhu, D., & Karthi, G. (2009) · International Conference on Advances in Computing, Control, and Telecommunication Technologies · doi:10.1109/act.2009.188 · Cited by 1 · see citing works
Authentication of biometric identification documents via mobile devices
Voloshynovskiy, S., Koval, O. J., Villan, R., Beekhof, F. P., & Pun, T. (2008) · Journal of Electronic Imaging · doi:10.1117/1.2896293 · Cited by 1 · see citing works
Implementation of a Novel Watermarking Technique for Devanagari Text
Patil, N. N. (2015) · International Journal of Information and Electronics Engineering · doi:10.7763/ijiee.2015.v5.557 · Cited by 1 · see citing works
Samphaiboon, N., & Dailey, M. N. (2010) · International Journal of Digital Crime and Forensics · doi:10.4018/jdcf.2010070104 · Cited by 1 · see citing works
Kermanidis, K. L. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15488-1_30
Content-Based Web Watermarking
Mir, N. (2013) · International Journal of Knowledge Society Research · doi:10.4018/ijksr.2013070107
Oh, J.-T., Kim, B. R., & Kim, W.-H. (2009) · The KIPS Transactions PartB · doi:10.3745/kipstb.2009.16-b.1.7
Text Watermarking Based on Syntactic Constituent Movement
Kim, M. (2009) · The KIPS Transactions PartB · doi:10.3745/kipstb.2009.16-b.1.79
Samphaiboon, N., & Dailey, M. N. (2012) · IGI Global eBooks · doi:10.4018/978-1-4666-1758-2.ch010
RTNLW: Reversible and Tamper-Aware Natural Language Watermarking Scheme for Multi-Stage Transmission
Chen, T., Liu, B., Li, W., Xu, Z. S., Xu, W., Zhang, X., & Yu, N. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462563
On the Combination and Evaluation of Structural Text Watermarking Methods
Bertini, F., Branchetti, S., Rizzo, S., & Montesi, D. (2026) · SN Computer Science · doi:10.1007/s42979-026-04995-6
- Authors
- Topkara, M., Taskiran, C. M., & Delp III, E. J.
- Affiliations
- Purdue University West Lafayette (US)
- Venue
- SPIE Proceedings
- Publisher
- SPIE
- Published
- 2005-03-21
- Volume
- 5681
- Pages
- 441
- ISSN
- 0277-786X (ISSN-L)
- OpenAlex
- W4252224706
- Cited by
- 63
- References
- 0
- Citations by year
- 2026: 2 · 2025: 4 · 2024: 1 · 2023: 2 · 2021: 1 · 2019: 1 · 2018: 1 · 2017: 1 · 2016: 3 · 2015: 1 · 2013: 3 · 2012: 6
- FWCI
- 4.16
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (publishedVersion)
- Funders
- Purdue University
- 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 › Cryptography and Data Security
- Keywords
- text watermarking, sentence constituents, text processing, image watermarking
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
