A Survey On Secure Machine Learning

2025-05-21

AI Summary

Secure multi-party computation (MPC) and machine learning (ML) face challenges in enabling privacy-preserving collaborative modeling across distributed data sources without exposing raw sensitive data. Method: This work systematically surveys existing SecureML protocols, establishing the first comprehensive taxonomy of MPC-ML techniques. It proposes a cross-layer MPC-ML optimization framework supporting both semi-honest and malicious adversary models, augmented with cryptographic auditability. A unified evaluation methodology quantifies performance trade-offs across three dimensions: data privacy preservation, model confidentiality, and robustness against adversarial attacks. Contribution/Results: The study advances theoretical foundations and engineering practices for privacy-enhancing distributed learning. It extends MPC-ML applicability to emerging domains such as game AI, offering principled design guidelines, formal security guarantees, and empirically validated efficiency–privacy–robustness bounds. The framework bridges gaps between cryptographic protocol design, ML system architecture, and real-world deployment constraints.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Safety and Robustness
• Multiagent Systems: Multiagent Learning

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Exploring secure multiparty computation for privacy-preserving machine learning
• Integrating MPC with ML frameworks for encrypted collaborative data analysis
• Evaluating SecureML libraries for data privacy and adversarial attack resilience

Innovation

• Secure multiparty computation enhances privacy-preserving ML
• Specialized frameworks optimize MPC integration in ML
• SecureML libraries include cryptographic and federated learning