k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text

arXiv:2402.11399v1 Announce Type: cross
Abstract: 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 …

abstract algorithms arxiv attacks clustering cs.cl cs.cr cs.cy cs.lg detection generated hashing language language generation lsh machine representation robustness semantic text token type vulnerable watermark watermarks