A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913404069871616 |
|---|---|
| author | Wu, Yihan Hu, Zhengmian Guo, Junfeng Zhang, Hongyang Huang, Heng |
| author_facet | Wu, Yihan Hu, Zhengmian Guo, Junfeng Zhang, Hongyang Huang, Heng |
| contents | Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge in the domain lies in preserving the distribution of original generated content after watermarking. Our research extends and improves upon existing watermarking framework, placing emphasis on the importance of a \textbf{Di}stribution-\textbf{P}reserving (DiP) watermark. Contrary to the current strategies, our proposed DiPmark simultaneously preserves the original token distribution during watermarking (distribution-preserving), is detectable without access to the language model API and prompts (accessible), and is provably robust to moderate changes of tokens (resilient). DiPmark operates by selecting a random set of tokens prior to the generation of a word, then modifying the token distribution through a distribution-preserving reweight function to enhance the probability of these selected tokens during the sampling process. Extensive empirical evaluation on various language models and tasks demonstrates our approach's distribution-preserving property, accessibility, and resilience, making it a effective solution for watermarking tasks that demand impeccable quality preservation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_07710 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models Wu, Yihan Hu, Zhengmian Guo, Junfeng Zhang, Hongyang Huang, Heng Cryptography and Security Computation and Language Machine Learning Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge in the domain lies in preserving the distribution of original generated content after watermarking. Our research extends and improves upon existing watermarking framework, placing emphasis on the importance of a \textbf{Di}stribution-\textbf{P}reserving (DiP) watermark. Contrary to the current strategies, our proposed DiPmark simultaneously preserves the original token distribution during watermarking (distribution-preserving), is detectable without access to the language model API and prompts (accessible), and is provably robust to moderate changes of tokens (resilient). DiPmark operates by selecting a random set of tokens prior to the generation of a word, then modifying the token distribution through a distribution-preserving reweight function to enhance the probability of these selected tokens during the sampling process. Extensive empirical evaluation on various language models and tasks demonstrates our approach's distribution-preserving property, accessibility, and resilience, making it a effective solution for watermarking tasks that demand impeccable quality preservation. |
| title | A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models |
| topic | Cryptography and Security Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2310.07710 |