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

TL;DR

k-SemStamp introduces a clustering-based semantic watermarking method that enhances robustness and efficiency in detecting machine-generated text, outperforming previous LSH-based approaches.

Contribution

It replaces LSH with k-means clustering for semantic partitioning, improving robustness and sampling efficiency in watermark detection.

Findings

k-SemStamp outperforms LSH-based SemStamp in robustness.

It maintains generation quality while improving detection efficiency.

Experimental results confirm enhanced detection performance.

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 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.