You are looking at a specific version 20200818:172927 of this paper. See the latest version.

Paper 2020/1002

CrypTFlow2: Practical 2-Party Secure Inference

Deevashwer Rathee and Mayank Rathee and Nishant Kumar and Nishanth Chandran and Divya Gupta and Aseem Rastogi and Rahul Sharma

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.

Metadata
Available format(s)
PDF
Category
Cryptographic protocols
Publication info
Published elsewhere. ACM CCS 2020
Keywords
secure two-party computationsecure inference
Contact author(s)
divya gupta @ microsoft com,nichandr @ microsoft com,rahsha @ microsoft com,aseemr @ microsoft com
History
2020-08-18: received
Short URL
https://ia.cr/2020/1002
License
Creative Commons Attribution
CC BY
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.