Privacy-preserving linear regression on distributed data with multiple keys

Ruan Ou; HuiYang Zhou

doi:10.1117/12.2652875

10 November 2022 Privacy-preserving linear regression on distributed data with multiple keys

Ruan Ou, HuiYang Zhou

Proceedings Volume 12331, International Conference on Mechanisms and Robotics (ICMAR 2022); 123312X (2022) https://doi.org/10.1117/12.2652875
Event: International Conference on Mechanisms and Robotics (ICMAR 2022), 2022, Zhuhai, China

Abstract

Linear regression is widely used as a tool for statistical analysis and is very popular as a technique to build predictive models in data mining field. Due to the fear of leakage of their privacy, data owners are reluctant to share data with others, while they wish to perform statistical analysis cooperatively. To solve the privacy issues, one of most popular approaches is to encrypt user’s data with public keys. However, this technique inevitably leads to another challenge that how to train linear regression based on encrypted data with multiple keys. In this work, we propose a privacy-preserving linear regression scheme base on a public-key cryptosystem with distributed two trapdoors to protect the privacy of the training data. We consider the problem of linear regression where the data are split up and held by different parties. We give details of how this scheme is implemented. Finally, we provide the theoretical analysis of the scheme.

Citation Download Citation

Ruan Ou and HuiYang Zhou "Privacy-preserving linear regression on distributed data with multiple keys", Proc. SPIE 12331, International Conference on Mechanisms and Robotics (ICMAR 2022), 123312X (10 November 2022); https://doi.org/10.1117/12.2652875

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available