Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.10185 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918243211411456 |
|---|---|
| author | Wang, Yangkun Shang, Jingbo |
| author_facet | Wang, Yangkun Shang, Jingbo |
| contents | A recent watermarking scheme for language models achieves distortion-free embedding and robustness to edit-distance attacks. However, it suffers from limited generation diversity and high detection overhead. In parallel, recent research has focused on undetectability, a property ensuring that watermarks remain difficult for adversaries to detect and spoof. In this work, we introduce a new class of watermarking schemes constructed through probabilistic automata. We present two instantiations: (i) a practical scheme with exponential generation diversity and computational efficiency, and (ii) a theoretical construction with formal undetectability guarantees under cryptographic assumptions. Extensive experiments on LLaMA-3B and Mistral-7B validate the superior performance of our scheme in terms of robustness and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Watermarks for Language Models via Probabilistic Automata Wang, Yangkun Shang, Jingbo Cryptography and Security Computation and Language A recent watermarking scheme for language models achieves distortion-free embedding and robustness to edit-distance attacks. However, it suffers from limited generation diversity and high detection overhead. In parallel, recent research has focused on undetectability, a property ensuring that watermarks remain difficult for adversaries to detect and spoof. In this work, we introduce a new class of watermarking schemes constructed through probabilistic automata. We present two instantiations: (i) a practical scheme with exponential generation diversity and computational efficiency, and (ii) a theoretical construction with formal undetectability guarantees under cryptographic assumptions. Extensive experiments on LLaMA-3B and Mistral-7B validate the superior performance of our scheme in terms of robustness and efficiency. |
| title | Watermarks for Language Models via Probabilistic Automata |
| topic | Cryptography and Security Computation and Language |
| url | https://arxiv.org/abs/2512.10185 |