Secure Computation for Machine Learning With SPDZ

By Valerie Chen, Valerio Pastro, Mariana Raykova. 2019

66 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Lichao Sun
3. Virginia Smith
4. Philip S. Yu
5. Yang Liu
6. Martin Jaggi
7. Lingjuan Lyu
8. Han Yu

In Information Systems

1. Lingjuan Lyu
2. Philip S. Yu
3. Jun Zhao
4. Jinhyun So
5. Divya Gupta
6. Virginia Smith
7. Ameet Talwalkar
8. Shreya Sharma

Citations in the corpus

• Federated Learning: Challenges, Methods, and Future Directions (2019, background): “Moreover, SMC protocols need to be carefully designed and implemented for each operation in the targeted learning algorithm [25, 79].”
• CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning (2019, methodology): “Furthermore, we empirically demonstrate the impact of CodedPrivateML by comparing it with the cryptographic approach based on secure multi-party computing (MPC) [9]–[12], that can also be applied to enable privacy-preserving machine learning tasks (e.g., see [13]–[18]).”
• Privacy and Robustness in Federated Learning: Attacks and Defenses (2020, background): “need to be carefully designed and implemented for each operation in the target learning algorithm [107], [108].”
• Secure Byzantine-Robust Machine Learning (2020, methodology): “One common setting for training machine learning model with MPC is the server-aided case [26, 9].”
• Secure and Efficient Federated Transfer Learning (2019, methodology): “[11] is another work in the active setting that shows linear regression and logistic regression using SPDZ can match similar latency as SecureML.”
• CrypTFlow2: Practical 2-Party Secure Inference (2020, background): “those that considered malicious adversaries [20, 36, 64] (for simpler ML models like linear models, regression, and polynomials)”
• A Scalable Approach for Privacy-Preserving Collaborative Machine Learning (2020, unknown): “…we empirically demonstrate the performance of COPML by comparing it with cryptographic benchmarks based on secure multi-party computing (MPC) [1], [2], [3], [4], that can also be applied to enable privacy-preserving machine learning tasks (e.g. see [5], [6], [7], [8], [9], [10], [11], [12]).”