Improved Multi-Party Fixed-Point Multiplication

ePrint Report: Improved Multi-Party Fixed-Point Multiplication

Saikrishna Badrinarayanan, Eysa Lee, Peihan Miao, Peter Rindal

Machine learning is widely used for a range of applications and is increasingly offered as a service by major technology companies. However, the required massive data collection raises privacy concerns during both training and inference. Privacy-preserving machine learning aims to solve this problem. In this setting, a collection of servers secret share their data and use secure multi-party computation to train and evaluate models on the …

applications collection companies data data collection eprint report lee machine machine learning major party peter point privacy privacy concerns report service technology training