A Different Level Text Protection Mechanism With Differential Privacy
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916383619547136 |
|---|---|
| author | Fu, Qingwen |
| author_facet | Fu, Qingwen |
| contents | The article introduces a method for extracting words of different degrees of importance based on the BERT pre-training model and proves the effectiveness of this method. The article also discusses the impact of maintaining the same perturbation results for words of different importance on the overall text utility. This method can be applied to long text protection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_03707 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Different Level Text Protection Mechanism With Differential Privacy Fu, Qingwen Computation and Language Artificial Intelligence The article introduces a method for extracting words of different degrees of importance based on the BERT pre-training model and proves the effectiveness of this method. The article also discusses the impact of maintaining the same perturbation results for words of different importance on the overall text utility. This method can be applied to long text protection. |
| title | A Different Level Text Protection Mechanism With Differential Privacy |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2409.03707 |