Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.16699 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909773272711168 |
|---|---|
| author | Ghanim, Mansour Al Xue, Jiaqi Hastuti, Rochana Prih Zheng, Mengxin Solihin, Yan Lou, Qian |
| author_facet | Ghanim, Mansour Al Xue, Jiaqi Hastuti, Rochana Prih Zheng, Mengxin Solihin, Yan Lou, Qian |
| contents | We present a study to benchmark representative watermarking methods in cross-lingual settings. The current literature mainly focuses on the evaluation of watermarking methods for the English language. However, the literature for evaluating watermarking in cross-lingual settings is scarce. This results in overlooking important adversary scenarios in which a cross-lingual adversary could be in, leading to a gray area of practicality over cross-lingual watermarking. In this paper, we evaluate four watermarking methods in four different and vocabulary rich languages. Our experiments investigate the quality of text under different watermarking procedure and the detectability of watermarks with practical translation attack scenarios. Specifically, we investigate practical scenarios that an adversary with cross-lingual knowledge could take, and evaluate whether current watermarking methods are suitable for such scenarios. Finally, from our findings, we draw key insights about watermarking in cross-lingual settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations Ghanim, Mansour Al Xue, Jiaqi Hastuti, Rochana Prih Zheng, Mengxin Solihin, Yan Lou, Qian Computation and Language Machine Learning We present a study to benchmark representative watermarking methods in cross-lingual settings. The current literature mainly focuses on the evaluation of watermarking methods for the English language. However, the literature for evaluating watermarking in cross-lingual settings is scarce. This results in overlooking important adversary scenarios in which a cross-lingual adversary could be in, leading to a gray area of practicality over cross-lingual watermarking. In this paper, we evaluate four watermarking methods in four different and vocabulary rich languages. Our experiments investigate the quality of text under different watermarking procedure and the detectability of watermarks with practical translation attack scenarios. Specifically, we investigate practical scenarios that an adversary with cross-lingual knowledge could take, and evaluate whether current watermarking methods are suitable for such scenarios. Finally, from our findings, we draw key insights about watermarking in cross-lingual settings. |
| title | Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2502.16699 |