Skip to main content
USENIX
  • Conferences
  • Students
Sign in
  • Home
  • Attend
    • Registration Information
    • Registration Discounts
    • Venue, Hotel, and Travel
    • Students and Grants
    • Co-located Workshops
  • Program
    • At a Glance
    • Technical Sessions
  • Activities
    • Birds-of-a-Feather Sessions
    • Poster Session
    • Work-in-Progress Reports (WiPs)
  • Sponsorship
  • Participate
    • Instructions for Authors and Speakers
    • Call for Papers
      • Important Dates
      • Symposium Organizers
      • Symposium Topics
      • Refereed Papers
      • Symposium Activities
      • Submitting Papers
  • About
    • Symposium Organizers
    • Questions
    • Services
    • Help Promote
    • Past Symposia
  • Home
  • Attend
  • Program
  • Activities
  • Sponsorship
  • Participate
  • About

sponsors

Platinum Sponsor
Gold Sponsor
Silver Sponsor
Silver Sponsor
Silver Sponsor
Silver Sponsor
Bronze Sponsor
Bronze Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Industry Partner
Industry Partner

help promote

USENIX Security '16 button

Get more
Help Promote graphics!

connect with usenix


  •  Twitter
  •  Facebook
  •  LinkedIn
  •  Google+
  •  YouTube

twitter

Tweets by USENIXSecurity

usenix conference policies

  • Event Code of Conduct
  • Conference Network Policy
  • Statement on Environmental Responsibility Policy

You are here

Home » Oblivious Multi-Party Machine Learning on Trusted Processors
Tweet

connect with us

Oblivious Multi-Party Machine Learning on Trusted Processors

Authors: 

Olga Ohrimenko, Felix Schuster, and Cédric Fournet, Microsoft Research; Aastha Mehta, Microsoft Research and Max Planck Institute for Software Systems (MPI-SWS); Sebastian Nowozin, Kapil Vaswani, and Manuel Costa, Microsoft Research

Abstract: 

Privacy-preserving multi-party machine learning allows multiple organizations to perform collaborative data analytics while guaranteeing the privacy of their individual datasets. Using trusted SGX-processors for this task yields high performance, but requires a careful selection, adaptation, and implementation of machine-learning algorithms to provably prevent the exploitation of any side channels induced by data-dependent access patterns.

We propose data-oblivious machine learning algorithms for support vector machines, matrix factorization, neural networks, decision trees, and k-means clustering. We show that our efficient implementation based on Intel Skylake processors scales up to large, realistic datasets, with overheads several orders of magnitude lower than with previous approaches based on advanced cryptographic multi-party computation schemes.

Olga Ohrimenko, Microsoft Research

Felix Schuster, Microsoft Research

Cédric Fournet, Microsoft Research

Aastha Mehta, Microsoft Research and Max Planck Institute for Software Systems (MPI-SWS)

Sebastian Nowozin, Microsoft Research

Kapil Vaswani, Microsoft Research

Manuel Costa, Microsoft Research

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {197247,
author = {Olga Ohrimenko and Felix Schuster and Cedric Fournet and Aastha Mehta and Sebastian Nowozin and Kapil Vaswani and Manuel Costa},
title = {Oblivious Multi-Party Machine Learning on Trusted Processors},
booktitle = {25th {USENIX} Security Symposium ({USENIX} Security 16)},
year = {2016},
isbn = {978-1-931971-32-4},
address = {Austin, TX},
pages = {619--636},
url = {https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/ohrimenko},
publisher = {{USENIX} Association},
month = aug,
}
Download
Ohrimenko PDF

Presentation Video

Presentation Audio

MP3 Download

Download Audio

  • Log in or    Register to post comments

Platinum Sponsors

Gold Sponsors

Silver Sponsors

Bronze Sponsors

Media Sponsors & Industry Partners

© USENIX

  • Privacy Policy
  • Conference Policies
  • Contact Us