Search Results for author:
Found 2 papers, 2 papers with code
Selective Differential Privacy for Language Modeling
Given that the private information in natural language is sparse (for example, the bulk of an email might not carry personally identifiable information), we propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data to improve model utility.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
