Privacy-Preserving Ridge Regression with only Linearly-Homomorphic Encryption
Lists
Only you see this
Abstract
Linear regression with 2-norm regularization (i.e., ridge regression) is an important statistical technique that models the relationship between some explanatory values and an outcome value using a linear function. In many applications (e.g., predictive modeling in personalized health-care), these values represent sensitive data owned by several different parties who are unwilling to share them. In this setting, training a linear regression model becomes challenging and needs specific cryptographic solutions. This problem was elegantly addressed by Nikolaenko et al. in S&P (Oakland) 2013. They suggested a two-server system that uses linearly-homomorphic encryption (LHE) and Yao’s two-party protocol (garbled circuits). In this work, we propose a novel system that can train a ridge linear regression model using only LHE (i.e., without using Yao’s protocol). This greatly improves the overall performance (both in computation and communication) as Yao’s protocol was the main bottleneck in the previous solution. The efficiency of the proposed system is validated both on synthetically-generated and real-world datasets.
BibTeX
@inproceedings{giacomelli2018privacy,
author = {Irene Giacomelli and Somesh Jha and Marc Joye and C. David Page and Kyonghwan Yoon},
title = {{Privacy-Preserving Ridge Regression with only Linearly-Homomorphic Encryption}},
booktitle = {ACNS},
year = {2018},
doi = {10.1007/978-3-319-93387-0\_13},
}| Privacy-Preserving Ridge Regression on Distributed Data | IACR ePrint · 2017 |
| Encrypted Accelerated Least Squares Regression | AISTATS · 2017 |
| Secure Linear Regression on Vertically Partitioned Datasets | IACR ePrint · 2016 |
| Logistic Regression on Homomorphic Encrypted Data at Scale | AAAI · 2019 |
| Efficient Logistic Regression on Large Encrypted Data | IACR ePrint · 2018 |
| Logistic regression model training based on the approximate homomorphic encryption | IACR ePrint · 2018 |