English

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

Computation and Language 2024-06-11 v2 Cryptography and Security Computers and Society Machine Learning

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.

Keywords

Cite

@article{arxiv.2402.11399,
  title  = {k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text},
  author = {Abe Bohan Hou and Jingyu Zhang and Yichen Wang and Daniel Khashabi and Tianxing He},
  journal= {arXiv preprint arXiv:2402.11399},
  year   = {2024}
}

Comments

Accepted to ACL 24 Findings

R2 v1 2026-06-28T14:51:59.849Z