Open Access

ARTICLE

A Privacy Preserving Deep Linear Regression Scheme Based on Homomorphic Encryption

Danping Dong^{1, *}, Yue Wu¹, Lizhi Xiong¹, Zhihua Xia¹

1 School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China.

* Corresponding Author: Danping Dong. Email: .

Journal on Big Data 2019, 1(3), 145-150. https://doi.org/10.32604/jbd.2019.08706

Abstract

This paper proposes a strategy for machine learning in the ciphertext domain. The data to be trained in the linear regression equation is encrypted by SHE homomorphic encryption, and then trained in the ciphertext domain. At the same time, it is guaranteed that the error of the training results between the ciphertext domain and the plaintext domain is in a controllable range. After the training, the ciphertext can be decrypted and restored to the original plaintext training data.

---

Keywords

---