PrivFT: Private and Fast Text Classification With Homomorphic Encryption

We present an efficient and non-interactive method for Text Classification while preserving the privacy of the content using Fully Homomorphic Encryption (FHE). Our solution (named Priv ate F ast T ext (PrivFT)) provides two services: 1) making inference of encrypted user inputs using a plaintext mo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2020, Vol.8, p.226544-226556
Main Authors: Badawi, Ahmad Al, Hoang, Louie, Mun, Chan Fook, Laine, Kim, Aung, Khin Mi Mi
Format: Article
Language:English
Subjects:
Classification
Cloud computing
Computational modeling
Cryptography
Data models
data privacy
data security
Datasets
Electronic mail
Encryption
Graphics processing units
graphics processors
homomorphic encryption
Inference
Natural language processing
Privacy
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present an efficient and non-interactive method for Text Classification while preserving the privacy of the content using Fully Homomorphic Encryption (FHE). Our solution (named Priv ate F ast T ext (PrivFT)) provides two services: 1) making inference of encrypted user inputs using a plaintext model and 2) training an effective model using an encrypted dataset. For inference, we use a pre-trained plaintext model and outline a system for homomorphic inference on encrypted user inputs with zero loss to prediction accuracy compared to the non-encrypted version. In the second part, we show how to train a supervised model using fully encrypted data to generate an encrypted model. For improved performance, we provide a GPU implementation of the Cheon-Kim-Kim-Song (CKKS) FHE scheme that shows 1 to 2 orders of magnitude speedup against existing implementations. We build PrivFT on top of our FHE engine in GPUs to achieve a run time per inference of 0.17 seconds for various Natural Language Processing (NLP) public datasets. Training on a relatively large encrypted dataset is more computationally intensive requiring 5.04 days.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.3045465