Helen: Maliciously Secure Coopetitive Learning for Linear Models

Many organizations wish to collaboratively train machine learning models on their combined datasets for a common benefit (e.g., better medical research, or fraud detection). However, they often cannot share their plaintext datasets due to privacy concerns and/or business competition. In this paper,...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE Symposium on Security and Privacy (SP) pp. 724 - 738
Main Authors Zheng, Wenting, Popa, Raluca Ada, Gonzalez, Joseph E., Stoica, Ion
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2019
Subjects
Convex functions
Cryptography
Data models
Linear-models
Machine learning
Organizations
Privacy
Protocols
Security
Training
Online AccessGet full text

Cover

More Information
Summary:Many organizations wish to collaboratively train machine learning models on their combined datasets for a common benefit (e.g., better medical research, or fraud detection). However, they often cannot share their plaintext datasets due to privacy concerns and/or business competition. In this paper, we design and build Helen, a system that allows multiple parties to train a linear model without revealing their data, a setting we call coopetitive learning. Compared to prior secure training systems, Helen protects against a much stronger adversary who is malicious and can compromise m−1 out of m parties. Our evaluation shows that Helen can achieve up to five orders of magnitude of performance improvement when compared to training using an existing state-of-the-art secure multi-party computation framework.
ISSN:2375-1207
DOI:10.1109/SP.2019.00045