Secure Computation for Machine Learning With SPDZ
It addresses privacy-preserving machine learning for sensitive data, but is incremental as it builds on existing MPC techniques.
This project tackled the efficiency problem of Secure Multi-Party Computation (MPC) for machine learning by evaluating the SPDZ framework, showing it outperforms previous semi-honest MPC implementations in applications like linear and logistic regression while providing stronger security.
Secure Multi-Party Computation (MPC) is an area of cryptography that enables computation on sensitive data from multiple sources while maintaining privacy guarantees. However, theoretical MPC protocols often do not scale efficiently to real-world data. This project investigates the efficiency of the SPDZ framework, which provides an implementation of an MPC protocol with malicious security, in the context of popular machine learning (ML) algorithms. In particular, we chose applications such as linear regression and logistic regression, which have been implemented and evaluated using semi-honest MPC techniques. We demonstrate that the SPDZ framework outperforms these previous implementations while providing stronger security.