A Survey On Secure Machine Learning
Taobo Liao, Taoran Li, Prathamesh Nadkarni
TL;DR
The paper surveys how secure multiparty computation enables privacy-preserving machine learning by examining key systems (CRYPTEN, Cerebro) and libraries (JustGarble, TFEncrypted, Crypten, LibOTe, OTExtension). It highlights SecureML as a scalable two-server MPC framework handling linear/logistic regression and neural networks via offline-online phases, supported by primitives such as OT, garbled circuits, and secret sharing with Beaver triplets. The discussion covers real-world deployment through Cerebro with a Python-like DSL, compiler optimizations, auditing mechanisms, and performance considerations, as well as applications in gaming and a range of MPC-powered ML workflows. The paper also reviews MP-SPDZ as a versatile MPC platform and summarizes the ecosystem of secure ML libraries, emphasizing practical trade-offs, security models, and potential impact across healthcare, finance, and beyond.
Abstract
In this survey, we will explore the interaction between secure multiparty computation and the area of machine learning. Recent advances in secure multiparty computation (MPC) have significantly improved its applicability in the realm of machine learning (ML), offering robust solutions for privacy-preserving collaborative learning. This review explores key contributions that leverage MPC to enable multiple parties to engage in ML tasks without compromising the privacy of their data. The integration of MPC with ML frameworks facilitates the training and evaluation of models on combined datasets from various sources, ensuring that sensitive information remains encrypted throughout the process. Innovations such as specialized software frameworks and domain-specific languages streamline the adoption of MPC in ML, optimizing performance and broadening its usage. These frameworks address both semi-honest and malicious threat models, incorporating features such as automated optimizations and cryptographic auditing to ensure compliance and data integrity. The collective insights from these studies highlight MPC's potential in fostering collaborative yet confidential data analysis, marking a significant stride towards the realization of secure and efficient computational solutions in privacy-sensitive industries. This paper investigates a spectrum of SecureML libraries that includes cryptographic protocols, federated learning frameworks, and privacy-preserving algorithms. By surveying the existing literature, this paper aims to examine the efficacy of these libraries in preserving data privacy, ensuring model confidentiality, and fortifying ML systems against adversarial attacks. Additionally, the study explores an innovative application domain for SecureML techniques: the integration of these methodologies in gaming environments utilizing ML.