Trident: Efficient 4PC Framework for Privacy Preserving Machine Learning

TL;DR

This paper introduces Trident, an efficient four-party privacy-preserving machine learning framework that improves upon existing protocols in terms of efficiency, communication, and practicality across various algorithms and settings.

Contribution

It presents a novel 4PC protocol with minimal circuit complexity, a flexible mixed-world framework, and optimized conversions, advancing the state-of-the-art in PPML efficiency and practicality.

Findings

Achieves up to 187x speedup in training over ABY3.

Reduces communication complexity by up to 18x.

Demonstrates practical efficiency in LAN and WAN settings.

Abstract

Machine learning has started to be deployed in fields such as healthcare and finance, which propelled the need for and growth of privacy-preserving machine learning (PPML). We propose an actively secure four-party protocol (4PC), and a framework for PPML, showcasing its applications on four of the most widely-known machine learning algorithms -- Linear Regression, Logistic Regression, Neural Networks, and Convolutional Neural Networks. Our 4PC protocol tolerating at most one malicious corruption is practically efficient as compared to the existing works. We use the protocol to build an efficient mixed-world framework (Trident) to switch between the Arithmetic, Boolean, and Garbled worlds. Our framework operates in the offline-online paradigm over rings and is instantiated in an outsourced setting for machine learning. Also, we propose conversions especially relevant to privacy-preserving machine learning. The highlights of our framework include using a minimal number of expensive circuits overall as compared to ABY3. This can be seen in our technique for truncation, which does not affect the online cost of multiplication and removes the need for any circuits in the offline phase. Our B2A conversion has an improvement of $\mathbf{7} \times$ in rounds and $\mathbf{18} \times$ in the communication complexity. The practicality of our framework is argued through improvements in the benchmarking of the aforementioned algorithms when compared with ABY3. All the protocols are implemented over a 64-bit ring in both LAN and WAN settings. Our improvements go up to $\mathbf{187} \times$ for the training phase and $\mathbf{158} \times$ for the prediction phase when observed over LAN and WAN.