Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption. (arXiv:2210.02574v1 [cs.CL])

Embeddings, which compress information in raw text into semantics-preserving
low-dimensional vectors, have been widely adopted for their efficacy. However,
recent research has shown that embeddings can potentially leak private
information about sensitive attributes of the text, and in some cases, can be
inverted to recover the original input text. To address these growing privacy
challenges, we propose a privatization mechanism for embeddings based on
homomorphic encryption, to prevent potential leakage of any piece of
information in the process of text …

arxiv bert classification encryption homomorphic encryption privacy text text classification