评估真实世界跨语言操作下文本水印的鲁棒性与准确性
Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations
AI总结：
本研究针对跨语言场景，评估四种文本水印方法在四种语言下的鲁棒性与准确性，探讨实际翻译攻击下的可检测性，并总结关键见解。
摘要：
我们提出了一项研究，旨在对跨语言环境下的代表性水印方法进行基准测试。当前文献主要关注英语水印方法的评估。然而，评估跨语言环境下水印的文献却很少。这导致忽视了跨语言攻击者可能处于的重要对抗场景，从而在跨语言水印的实际应用上留下了一个灰色地带。在本文中，我们在四种词汇丰富的语言中评估了四种水印方法。我们的实验考察了不同水印程序下文本的质量，以及在实际翻译攻击场景下水印的可检测性。具体来说，我们研究了具备跨语言知识的攻击者可能采取的实际场景，并评估当前水印方法是否适用于此类场景。最后，根据我们的发现，我们得出了关于跨语言环境下水印的关键见解。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
