Sentence-level Privacy for Document Embeddings. (arXiv:2205.04605v1 [cs.LG])

Web: http://arxiv.org/abs/2205.04605

User language data can contain highly sensitive personal content. As such, it
is imperative to offer users a strong and interpretable privacy guarantee when
learning from their data. In this work, we propose SentDP: pure local
differential privacy at the sentence level for a single user document. We
propose a novel technique, DeepCandidate, that combines concepts from robust
statistics and language modeling to produce high-dimensional, general-purpose
$\epsilon$-SentDP document embeddings. This guarantees that any single sentence
in a document can be …

arxiv privacy