Maliciously Secure Matrix Multiplication with Applications to Private Deep Learning (Prof. Miran Kim)
Maliciously Secure Matrix Multiplication with Applications to Private Deep Learning
Hao Chen and Miran Kim and Ilya Razenshteyn and Dragos Rotaru and Yongsoo Song and Sameer Wagh
Abstract: Computing on data in a manner that preserve the privacy is of growing importance. Multi-Party Computation (MPC) and Homomorphic Encryption (HE) are two cryptographic techniques for privacy-preserving computations. In this work, we have developed efficient UC-secure multiparty protocols for matrix multiplications and two-dimensional convolutions. We built upon the SPDZ framework and integrated the state-of-the-art HE algorithms for matrix multiplication. Our protocol achieved communication cost linear only in the input and output dimensions and not on the number of multiplication operations. We eliminate the ``triple sacrifice'' step of SPDZ to improve efficiency and simplify the zero-knowledge proofs. We implemented our protocols and benchmarked them against the SPDZ LowGear variant (Keller et al. Eurocrypt'18). For multiplying two square matrices of size 128, we reduced the communication cost from 1.54 GB to 12.46 MB, an improvement of over two orders of magnitude that only improves with larger matrix sizes. For evaluating all convolution layers of the ResNet-50 neural network, the communication reduces cost from 5 TB to 41 GB.
Category / Keywords: cryptographic protocols / cryptographic protocols, multi-party computation, homomorphic encryption
Original Publication (with minor differences): AsiaCrypt 2020
Date: received 17 Apr 2020, last revised 15 Sep 2020
Contact author: swagh at princeton edu,haoche@microsoft com,miran kim@uth tmc edu,ilyaraz@microsoft com,dragos rotaru@esat kuleuven be,yongsoo song@microsoft com
Note: Extended version of the published paper.
Short URL: ia.cr/2020/451