25th USENIX Security Symposium has ended
Back To Schedule
Thursday, August 11 • 2:30pm - 3:00pm
Oblivious Multi-Party Machine Learning on Trusted Processors

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

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.


Manuel Costa

Microsoft Research, Cambridge

Aastha Mehta

Max Planck Institute for Software Systems (MPI-SWS)

Olya Ohrimenko

Microsoft Research, Cambridge

Thursday August 11, 2016 2:30pm - 3:00pm PDT
Zilker Ballroom 3