pith. sign in

arxiv: 2402.11399 · v2 · pith:2VJZ7QW2new · submitted 2024-02-17 · 💻 cs.CL · cs.CR· cs.CY· cs.LG

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

classification 💻 cs.CL cs.CRcs.CYcs.LG
keywords semanticdetectiongenerationk-semstamprobustnesssemstampeffectivemachine-generated
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

    cs.CR 2025-08 accept novelty 7.0

    A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.

  2. SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

    cs.CR 2026-05 unverdicted novelty 6.0

    SAMark uses self-anchored semantic green regions, multi-channel hyperbolic scoring, and diversity-aware filtering to reach 90.2% TP@FP1% detection under paragraph paraphrasing while preserving text quality.

  3. TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection

    cs.CR 2026-05 unverdicted novelty 6.0

    TextSeal provides a localized, distortion-free LLM watermark that enables provenance tracking and distillation detection while preserving performance and text quality.

  4. TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection

    cs.CR 2026-05 unverdicted novelty 6.0

    TextSeal provides a localized, distortion-free LLM watermark that outperforms baselines in detection strength, remains effective in mixed human-AI text, preserves model performance, and transfers through distillation ...