k-SemStamp：一种基于聚类的语义水印，用于检测机器生成文本
k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
AI总结：
本文提出k-SemStamp，用k-means聚类替代SemStamp中的LSH来划分语义空间，在保持生成质量的同时显著提升机器生成文本检测的鲁棒性和采样效率。
摘要：
近期带水印的生成算法在语言生成过程中注入可检测签名，以便于事后检测。虽然词元级水印容易受到改写攻击，但SemStamp（Hou等，2023）将水印施加在句子的语义表示上，并展现出良好的鲁棒性。SemStamp采用局部敏感哈希（LSH）以任意超平面划分语义空间，这导致鲁棒性与速度之间的折中不够理想。我们提出k-SemStamp，这是对SemStamp的一种简单而有效的增强，利用k-means聚类替代LSH，在感知内在语义结构的情况下划分嵌入空间。实验结果表明，k-SemStamp显著提高了鲁棒性和采样效率，同时保持了生成质量，为机器生成文本检测提供了一种更有效的工具。
英文摘要：
Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection. While token-level watermarks are vulnerable to paraphrase attacks, SemStamp (Hou et al., 2023) applies watermark on the semantic representation of sentences and demonstrates promising robustness. SemStamp employs locality-sensitive hashing (LSH) to partition the semantic space with arbitrary hyperplanes, which results in a suboptimal tradeoff between robustness and speed. We propose k-SemStamp, a simple yet effective enhancement of SemStamp, utilizing k-means clustering as an alternative of LSH to partition the embedding space with awareness of inherent semantic structure. Experimental results indicate that k-SemStamp saliently improves its robustness and sampling efficiency while preserving the generation quality, advancing a more effective tool for machine-generated text detection.
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。
