Accelerating 2PC-based ML with Limited Trusted Hardware

2020/09/11 by Muqsit Nawaz, Nawaz, Muqsit, Aditya Gulati +9
Computer Science · #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Physical Unclonable Functions (PUFs) and Hardware Security #Security and Verification in Computing

paper · pdf · doi:10.48550/arxiv.2009.05566

openalex publication_date 2020/09/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper describes the design, implementation, and evaluation of Otak, a system that allows two non-colluding cloud providers to run machine learning (ML) inference without knowing the inputs to inference. Prior work for this problem mostly relies on advanced cryptography such as two-party secure computation (2PC) protocols that provide rigorous guarantees but suffer from high resource overhead. Otak improves efficiency via a new 2PC protocol that (i) tailors recent primitives such as function and homomorphic secret sharing to ML inference, and (ii) uses trusted hardware in a limited capacity to bootstrap the protocol. At the same time, Otak reduces trust assumptions on trusted hardware by running a small code inside the hardware, restricting its use to a preprocessing step, and distributing trust over heterogeneous trusted hardware platforms from different vendors. An implementation and evaluation of Otak demonstrates that its CPU and network overhead converted to a dollar amount is 5.4-385× lower than state-of-the-art 2PC-based works. Besides, Otak's trusted computing base (code inside trusted hardware) is only 1,300 lines of code, which is 14.6-29.2× lower than the code-size in prior trusted hardware-based works.

Citations

• Crypto-Nets: Neural Networks over Encrypted Data
• New directions in cryptography
• ImageNet classification with deep convolutional neural networks
• Inferring Fine-grained Control Flow Inside SGX Enclaves with Branch\n Shadowing
• CryptoDL: Deep Neural Networks over Encrypted Data
• Chiron: Privacy-preserving Machine Learning as a Service
• Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
• Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
• Low Latency Privacy Preserving Inference
• Secure Computation for Machine Learning With SPDZ
• Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environments
• Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data

Related

• MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inference
• Locking Machine Learning Models into Hardware
• Confidential Computing across Edge-to-Cloud for Machine Learning: A Survey Study
• DASH: Accelerating Distributed Private Machine Learning Inference with Arithmetic Garbled Circuits
• Robust and Verifiable MPC with Applications to Linear Machine Learning Inference