测试四种水印方法在跨语言场景下的鲁棒性与准确性
Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations
- 在四种高词汇量语言中评估水印方法
- 发现现有方法在跨语言翻译攻击下易失效
- 为多语言内容保护提供关键实践建议
我们对跨语言场景下的代表性文本水印方法进行了基准测试。当前文献主要聚焦英文水印评估，而跨语言水印评估研究匮乏，导致忽视了实际中可能遭遇的跨语言攻击场景，使跨语言水印的实际应用存在盲区。本文在四种不同且词汇丰富的语言中评估了四种水印方法，考察了不同水印处理下文本质量以及在真实翻译攻击场景中的可检测性。具体分析了具备跨语言知识的攻击者可能采取的策略，并评估现有水印方法在这些场景下的适用性。最终，基于实验结果，提炼出关于跨语言水印的关键洞见。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。