English

SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation

Computation and Language 2024-04-23 v2

Abstract

Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive hashing (LSH), which partitions the semantic space of sentences. The algorithm encodes and LSH-hashes a candidate sentence generated by an LLM, and conducts sentence-level rejection sampling until the sampled sentence falls in watermarked partitions in the semantic embedding space. A margin-based constraint is used to enhance its robustness. To show the advantages of our algorithm, we propose a "bigram" paraphrase attack using the paraphrase that has the fewest bigram overlaps with the original sentence. This attack is shown to be effective against the existing token-level watermarking method. Experimental results show that our novel semantic watermark algorithm is not only more robust than the previous state-of-the-art method on both common and bigram paraphrase attacks, but also is better at preserving the quality of generation.

Keywords

Cite

@article{arxiv.2310.03991,
  title  = {SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation},
  author = {Abe Bohan Hou and Jingyu Zhang and Tianxing He and Yichen Wang and Yung-Sung Chuang and Hongwei Wang and Lingfeng Shen and Benjamin Van Durme and Daniel Khashabi and Yulia Tsvetkov},
  journal= {arXiv preprint arXiv:2310.03991},
  year   = {2024}
}

Comments

Accepted to NAACL 24 Main

R2 v1 2026-06-28T12:42:13.928Z