Secure Computation for Machine Learning With SPDZ
arXiv:1901.00329
Abstract
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.
32nd Conference on Neural Information Processing Systems (NIPS 2018)
Cited by in corpus (11)
- CrypTFlow2: Practical 2-Party Secure Inference
- Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
- Secure Byzantine-Robust Machine Learning
- A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
- Privacy-Preserving Energy Storage Sharing with Blockchain and Secure Multi-Party Computation
- When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control
- Privacy-preserving Decentralized Aggregation for Federated Learning
- Harmonic Coding: An Optimal Linear Code for Privacy-Preserving Gradient-Type Computation
- Revisiting Secure Computation Using Functional Encryption: Opportunities and Research Directions
- Accelerating 2PC-based ML with Limited Trusted Hardware
- Corella: A Private Multi Server Learning Approach based on Correlated Queries