Text Watermarking 2027
Synopsis
- Task: Insert a watermark into a given text. Then, after we have attacked the text, detect the inserted watermark.
- Registration: TBA.
- Important dates: TBA.
- Data: TBA.
- Evaluation Measures: TBA.
- Baselines: TBA.
Task Overview
In the Text Watermarking task, participants are given a text and must insert a watermark into it. After submitting the watermark system, including a watermark detection algorithm, the watermark system is run on the test dataset. The watermarked texts are then subjected to various attacks. The objective is to detect the watermark after the text has been attacked, thereby demonstrating its robustness against an attacker.
Further details are announced later.
Data
TBA.
Submission
TBA.
Evaluation
TBA.
Baselines
TBA.
Leaderboard
TBD
Related Work
- John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, and Tom Goldstein. A watermark for large language models. In Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett, editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Pro- ceedings of Machine Learning Research, pages 1706117084. PMLR, 2023. URL https://proceedings.mlr.press/v202/kirchenbauer23a.html
- Yapei Chang, Kalpesh Krishna, Amir Houmansadr, John Wieting, and Mo- hit Iyyer. Postmark: A robust blackbox watermark for large language models. In Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen, edi- tors, Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, November 12-16, 2024, pages 89698987. Association for Computational Linguistics, 2024. doi: 10.18653/V1/2024.EMNLP-MAIN.506. URL https://doi.org/10. 18653/v1/2024.emnlp-main.506.
- Xuandong Zhao, Prabhanjan Vijendra Ananth, Lei Li, and Yu-Xiang Wang. Provable robust watermarking for ai-generated text. In The Twelfth Interna- tional Conference on Learning Representations, ICLR 2024, Vienna, Aus- tria, May 7-11, 2024. OpenReview.net, 2024. URL https://openreview. net/forum?id=SsmT8aO45L.
- Yijian Lu, Aiwei Liu, Dianzhi Yu, Jingjing Li, and Irwin King. An entropy- based text watermarking detection method. In Lun-Wei Ku, Andre Martins, and Vivek Srikumar, editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024, pages 1172411735. Association for Computational Linguistics, 2024. doi: 10.18653/V1/2024. ACL-LONG.630. URL https://doi.org/10.18653/v1/2024.acl-long. 630.
- Taehyun Lee, Seokhee Hong, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin, and Gunhee Kim. Who wrote this code? watermarking for code generation. In Lun-Wei Ku, Andre Martins, and Vivek Sriku- mar, editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024, pages 48904911. Association for Compu- tational Linguistics, 2024. doi: 10.18653/V1/2024.ACL-LONG.268. URL https://doi.org/10.18653/v1/2024.acl-long.268.
- Aiwei Liu, Leyi Pan, Yijian Lu, Jingjing Li, Xuming Hu, Lijie Wen, Irwin King, and Philip S. Yu. A survey of text watermarking in the era of large language models. CoRR, abs/2312.07913, 2023. doi: 10.48550/ARXIV.2312.07913. URL https://doi.org/10.48550/arXiv.2312.07913.




