Visible to the public CrypTFlow: Secure TensorFlow Inference

TitleCrypTFlow: Secure TensorFlow Inference
Publication TypeConference Paper
Year of Publication2020
AuthorsKumar, N., Rathee, M., Chandran, N., Gupta, D., Rastogi, A., Sharma, R.
Conference Name2020 IEEE Symposium on Security and Privacy (SP)
Date Publishedmay
KeywordsAramis, Benchmark testing, compiler security, compositionality, CrypTFlow, cryptographic protocols, cryptography, data privacy, end-to-end compiler, Hardware, ImageNet dataset, improved semihonest 3-party protocol, inference accuracy, inference mechanisms, Logistics, malicious secure MPC protocols, malicious security, Metrics, plaintext TensorFlow, Porthos, program compilers, Protocols, pubcrawl, public key cryptography, Resiliency, Scalability, secure multiparty computation protocols, Secure TensorFlow inference, semihonest MPC protocol, semihonest security, Task Analysis, TensorFlow inference code
AbstractWe 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.
Citation Keykumar_cryptflow_2020