CrypTFlow2: Practical 2-Party Secure Inference
Authors:
Open Access
- 30 October 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 325-342
Abstract
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both correct -- i.e., their outputs are bitwise equivalent to the cleartext execution -- and efficient -- they outperform the state-of-the-art protocols in both latency and scale. At the core of CrypTFlow2, we have new 2PC protocols for secure comparison and division, designed carefully to balance round and communication complexity for secure inference tasks. Using CrypTFlow2, we present the first secure inference over ImageNet-scale DNNs like ResNet50 and DenseNet121. These DNNs are at least an order of magnitude larger than those considered in the prior work of 2-party DNN inference. Even on the benchmarks considered by prior work, CrypTFlow2 requires an order of magnitude less communication and 20x-30x less time than the state-of-the-art.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Oblivious Neural Network Predictions via MiniONN Transformations2017
- Pushing the Communication Barrier in Secure Computation using Lookup Tables2017
- Machine Learning Classification over Encrypted Data2015
- Efficient Garbling from a Fixed-Key Blockcipher2013
- More efficient oblivious transfer and extensions for faster secure computation2013
- Fully homomorphic encryption using ideal lattices2009
- Security and Composition of Multiparty Cryptographic ProtocolsJournal of Cryptology, 2000
- Correlated pseudorandomness and the complexity of private computations1996
- A randomized protocol for signing contractsCommunications of the ACM, 1985
- How to share a secretCommunications of the ACM, 1979