Conference item icon

Conference item

QUOTIENT: two-party secure neural network training and prediction

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 th...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1145/3319535.3339819

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
Wolfson College
Role:
Author
Publisher:
Association for Computing Machinery Publisher's website
Pages:
1231–1247
Host title:
CCS '19: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security
Publication date:
2019-11-06
Acceptance date:
2019-05-09
Event title:
26th ACM Conference on Computer and Communications (ACM CCS 2019)
Event location:
London, UK
Event website:
https://ccs19.swenjacobs.com/
Event start date:
2019-11-11T00:00:00Z
Event end date:
2019-11-15T00:00:00Z
DOI:
ISBN:
9781450367479
Language:
English
Keywords:
Pubs id:
1196459
Local pid:
pubs:1196459
Deposit date:
2021-09-29

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP