k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910477319143424 |
|---|---|
| author | Hou, Abe Bohan Zhang, Jingyu Wang, Yichen Khashabi, Daniel He, Tianxing |
| author_facet | Hou, Abe Bohan Zhang, Jingyu Wang, Yichen Khashabi, Daniel He, Tianxing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11399 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text Hou, Abe Bohan Zhang, Jingyu Wang, Yichen Khashabi, Daniel He, Tianxing Computation and Language Cryptography and Security Computers and Society Machine Learning 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. |
| title | k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text |
| topic | Computation and Language Cryptography and Security Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2402.11399 |