CrypTFlow: Secure TensorFlow Inference
Authors:
Top Cited Papers
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 336-353
Abstract
We present CrypTFlow, a first of its kind system that converts TensorFlow inference code into Secure Multi-party Computation (MPC) protocols at the push of a button. To do this, we build three components. Our first component, Athos, is an end-to-end compiler from TensorFlow to a variety of semihonest MPC protocols. The second component, Porthos, is an improved semi-honest 3-party protocol that provides significant speedups for TensorFlow like applications. Finally, to provide malicious secure MPC protocols, our third component, Aramis, is a novel technique that uses hardware with integrity guarantees to convert any semi-honest MPC protocol into an MPC protocol that provides malicious security. The malicious security of the protocols output by Aramis relies on integrity of the hardware and semi-honest security of MPC. Moreover, our system matches the inference accuracy of plaintext TensorFlow.We experimentally demonstrate the power of our system by showing the secure inference of real-world neural networks such as ResNet50 and DenseNet121 over the ImageNet dataset with running times of about 30 seconds for semi-honest security and under two minutes for malicious security. Prior work in the area of secure inference has been limited to semi-honest security of small networks over tiny datasets such as MNIST or CIFAR. Even on MNIST/CIFAR, CrypTFlow outperforms prior work.Keywords
All Related Versions
This publication has 51 references indexed in Scilit:
- Time to Rethink: Trust Brokerage Using Trusted Execution Environments2015
- VC3: Trustworthy Data Analytics in the Cloud Using SGX2015
- ObliVM: A Programming Framework for Secure Computation2015
- Machine Learning Classification over Encrypted Data2015
- ABY - A Framework for Efficient Mixed-Protocol Secure Two-Party Computation2015
- Secure two-party computations in ANSI C2012
- Secure Multi-Party Computation of Boolean Circuits with Applications to Privacy in On-Line Marketplaces2012
- Sharemind: A Framework for Fast Privacy-Preserving Computations2008
- Security and Composition of Multiparty Cryptographic ProtocolsJournal of Cryptology, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998