In this study, we delve into the hidden threats posed to text watermarking by users with cross-lingual knowledge. While most research focuses on watermarking methods for English, there is a significant gap in evaluating these methods in cross-lingual contexts. This oversight neglects critical adversary scenarios involving cross-lingual users, creating uncertainty regarding the effectiveness of cross-lingual watermarking. We assess four watermarking techniques across four linguistically rich languages, examining watermark resilience and text quality across various parameters and attacks. Our focus is on a realistic scenario featuring adversaries with cross-lingual expertise, evaluating the adequacy of current watermarking methods against such challenges.
View on arXiv@article{ghanim2025_2502.16699,
title={ Uncovering the Hidden Threat of Text Watermarking from Users with Cross-Lingual Knowledge },
author={ Mansour Al Ghanim and Jiaqi Xue and Rochana Prih Hastuti and Mengxin Zheng and Yan Solihin and Qian Lou },
journal={arXiv preprint arXiv:2502.16699},
year={ 2025 }
}