Agrawal, N;
Kusner, MJ;
Shamsabadi, AS;
Gascón, A;
(2019)
QUOTIENT: Two-party secure neural network training and prediction.
In:
Proceedings of the ACM Conference on Computer and Communications Security.
(pp. pp. 1231-1247).
ACM: New York, NY, USA.
Preview |
Text
1907.03372v1.pdf - Accepted Version Download (1MB) | Preview |
Abstract
Recently, there has been a wealth of effort devoted to the design of secure protocols for machine learning tasks. Much of this is aimed at enabling secure prediction from highly-accurate Deep Neural Networks (DNNs). However, as DNNs are trained on data, a key question is how such models can be also trained securely. The few prior works on secure DNN training have focused either on designing custom protocols for existing training algorithms, or on developing tailored training algorithms and then applying generic secure protocols. In this work, we investigate the advantages of designing training algorithms alongside a novel secure protocol, incorporating optimizations on both fronts. We present QUOTIENT, a new method for discretized training of DNNs, along with a customized secure two-party protocol for it. QUOTIENT incorporates key components of state-of-the-art DNN training such as layer normalization and adaptive gradient methods, and improves upon the state-of-the-art in DNN training in two-party computation. Compared to prior work, we obtain an improvement of 50X in WAN time and 6% in absolute accuracy.
| Type: | Proceedings paper |
|---|---|
| Title: | QUOTIENT: Two-party secure neural network training and prediction |
| Event: | 2019 ACM SIGSAC Conference on Computer and Communications Security (CCS '19) |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3319535.3339819 |
| Publisher version: | https://doi.org/10.1145/3319535.3339819 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Security and privacy, Cryptography, Cryptanalysis and other attacks, Security services, Privacy-preserving protocols |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10088321 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
