Secure Multi-Party Computation Approaches
Michael Chen, Elias Chias
Published: October 2023
Cryptology ePrint
Abstract
This research introduces a novel Secure Multi-Party Computation (SMPC) protocol optimized for distributed healthcare data analysis. Our framework achieves 2.8x faster secure computation compared to standard GMW-based approaches while maintaining full confidentiality of patient records across 14 clinical research institutions. The solution supports complex ML model inference with privacy guarantees through oblivious evaluation circuits and threshold-based decryption.
Key Contributions
- • Optimized oblivious transfer protocols
- • Threshold cryptography implementation
- • Real-world validation with 14 medical institutions
Impact
- • Citations: 98
- • Research Interest: 643
- • Saved by: 214 researchers
Related Publications
Privacy-Preserving Federated Learning
Elias Chias et al. 2024
Differential Privacy in Medical Machine Learning
Sarah Lin et al. 2024
Federated Learning with Enhanced Privacy
Elias Chias et al. 2025
Citation
@article{chen2023secure,
title={Secure Multi-Party Computation Approaches},
author={Chen, Michael and Chias, Elias},
journal={Cryptology ePrint Archive},
year={2023},
volume={2023/1024},
note={Available at: IACR ePrint Archive}
}