CrypTen: Secure Multi-Party Computation Meets Machine Learning

2021/09/02 by Brian Knott, Knott, Brian, Shobha Venkataraman +9 · 16 citations
Computer Science · #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques

paper · pdf · doi:10.48550/arxiv.2109.00984

openalex publication_date 2021/09/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Secure multi-party computation (MPC) allows parties to perform computations on data while keeping that data private. This capability has great potential for machine-learning applications: it facilitates training of machine-learning models on private data sets owned by different parties, evaluation of one party's private model using another party's private data, etc. Although a range of studies implement machine-learning models via secure MPC, such implementations are not yet mainstream. Adoption of secure MPC is hampered by the absence of flexible software frameworks that "speak the language" of machine-learning researchers and engineers. To foster adoption of secure MPC in machine learning, we present CrypTen: a software framework that exposes popular secure MPC primitives via abstractions that are common in modern machine-learning frameworks, such as tensor computations, automatic differentiation, and modular neural networks. This paper describes the design of CrypTen and measure its performance on state-of-the-art models for text classification, speech recognition, and image classification. Our benchmarks show that CrypTen's GPU support and high-performance communication between (an arbitrary number of) parties allows it to perform efficient private evaluation of modern machine-learning models under a semi-honest threat model. For example, two parties using CrypTen can securely predict phonemes in speech recordings using Wav2Letter faster than real-time. We hope that CrypTen will spur adoption of secure MPC in the machine-learning community.

Citations

• Poisoning Attacks against Support Vector Machines
• Gradient-based learning applied to document recognition
• Neural Architecture Search with Reinforcement Learning
• Gazelle: A Low Latency Framework for Secure Neural Network Inference
• DARTS: Differentiable Architecture Search
• A generic framework for privacy preserving deep learning
• MLP-Mixer: An all-MLP Architecture for Vision

Cited by

• DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inference
• An LLVM-Based Optimization Pipeline for SPDZ
• Differential Privacy for Secure Machine Learning in Healthcare IoT-Cloud Systems
• PrivLLMSwarm: Privacy-Preserving LLM-Driven UAV Swarms for Secure IoT Surveillance
• Private Data Imputation
• PraxiMLP: A Threshold-based Framework for Efficient Three-Party MLP with Practical Security
• SLIP-SEC: Formalizing Secure Protocols for Model IP Protection
• Intelligent AI Delegation
• Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference
• N-Parties Private Structure and Parameter Learning for Sum-Product Networks
• Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs
• ORQ: Complex Analytics on Private Data with Strong Security Guarantees
• CryptGNN: Enabling Secure Inference for Graph Neural Networks
• SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) Applications
• On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions
• CryptPEFT: Efficient and Private Neural Network Inference via Parameter-Efficient Fine-Tuning
• Privacy-Preserving Inference for Quantized BERT Models

Related

• MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inference
• The Communication-Friendly Privacy-Preserving Machine Learning against Malicious Adversaries
• CryptoNN: Training Neural Networks over Encrypted Data
• A Survey On Secure Machine Learning
• DASH: Accelerating Distributed Private Machine Learning Inference with Arithmetic Garbled Circuits