SIMC 2.0: Improved Secure ML Inference Against Malicious Clients

TL;DR

This paper introduces SIMC 2.0, an optimized secure machine learning inference protocol that significantly reduces computational and communication overheads, enabling faster and more practical privacy-preserving ML inference against malicious clients.

Contribution

SIMC 2.0 enhances secure ML inference by optimizing homomorphic computations and reducing garbled circuit size, achieving substantial speedups over previous methods.

Findings

Up to 17.4x speedup in linear layer computation

At least 1.3x reduction in overhead for non-linear layers

2.3 to 4.3x runtime improvement on state-of-the-art models

Abstract

In this paper, we study the problem of secure ML inference against a malicious client and a semi-trusted server such that the client only learns the inference output while the server learns nothing. This problem is first formulated by Lehmkuhl \textit{et al.} with a solution (MUSE, Usenix Security'21), whose performance is then substantially improved by Chandran et al.'s work (SIMC, USENIX Security'22). However, there still exists a nontrivial gap in these efforts towards practicality, giving the challenges of overhead reduction and secure inference acceleration in an all-round way. We propose SIMC 2.0, which complies with the underlying structure of SIMC, but significantly optimizes both the linear and non-linear layers of the model. Specifically, (1) we design a new coding method for homomorphic parallel computation between matrices and vectors. It is custom-built through the insight into the complementarity between cryptographic primitives in SIMC. As a result, it can minimize the number of rotation operations incurred in the calculation process, which is very computationally expensive compared to other homomorphic operations e.g., addition, multiplication). (2) We reduce the size of the garbled circuit (GC) (used to calculate nonlinear activation functions, e.g., ReLU) in SIMC by about two thirds. Then, we design an alternative lightweight protocol to perform tasks that are originally allocated to the expensive GCs. Compared with SIMC, our experiments show that SIMC 2.0 achieves a significant speedup by up to $17.4\times $ for linear layer computation, and at least $1.3\times$ reduction of both the computation and communication overheads in the implementation of non-linear layers under different data dimensions. Meanwhile, SIMC 2.0 demonstrates an encouraging runtime boost by $2.3\sim 4.3\times$ over SIMC on different state-of-the-art ML models.