activity
20182023
most citedQUOTIENT: Two-Party Secure Neural Network Training and Prediction

29 citations · 43 across the 4 of their papers we have counts for

collaborators
Showing cs.CRShow all

6 papers · 1 filter

cs.CR2020

PrivEdge: From Local to Distributed Private Training and Prediction

Ali Shahin Shamsabadi, Adria Gascon, Hamed Haddadi +1

Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user…

cs.CR201913 cited

Improved Summation from Shuffling

Borja Balle, James Bell, Adria Gascon +1

A protocol by Ishai et al.\ (FOCS 2006) showing how to implement distributed -party summation from secure shuffling has regained relevance in the context of the recently propose…

cs.CR201929 cited

QUOTIENT: Two-Party Secure Neural Network Training and Prediction

Nitin Agrawal, Ali Shahin Shamsabadi, Matt J. Kusner +1

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-ac…

cs.CR2019

Differentially Private Summation with Multi-Message Shuffling

Borja Balle, James Bell, Adria Gascon +1

In recent work, Cheu et al. (Eurocrypt 2019) proposed a protocol for -party real summation in the shuffle model of differential privacy with error and $Θ(ε\sqrt{n}…

cs.CR2018

TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service

Amartya Sanyal, Matt J. Kusner, Adrià Gascón +1

Machine learning methods are widely used for a variety of prediction problems. \emph{Prediction as a service} is a paradigm in which service providers with technological expertise…

cs.CR2018

How to Simulate It in Isabelle: Towards Formal Proof for Secure Multi-Party Computation

David Butler, David Aspinall, Adria Gascon

In cryptography, secure Multi-Party Computation (MPC) protocols allow participants to compute a function jointly while keeping their inputs private. Recent breakthroughs are bringi…