Publications

Detailed Information

Maliciously Secure Matrix Multiplication with Applications to Private Deep Learning

Cited 0 time in Web of Science Cited 13 time in Scopus
Authors

Chen, Hao; Kim, Miran; Razenshteyn, Ilya; Rotaru, Dragos; Song, Yongsoo; Wagh, Sameer

Issue Date
2020-12
Publisher
Springer Verlag
Citation
Lecture Notes in Computer Science, Vol.12493, pp.31-59
Abstract
© 2020, International Association for Cryptologic Research.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. Eurocrypt18). 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.
ISSN
0302-9743
URI
https://hdl.handle.net/10371/201199
DOI
https://doi.org/10.1007/978-3-030-64840-4_2
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Related Researcher

  • College of Engineering
  • Dept. of Computer Science and Engineering
Research Area Cryptography, Privacy, Security

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share