Computer Science Seminar: Olya Ohrimenko from Microsoft Research
Host: Karl Levitt
When: Thursday, April 13th at 3:10pm
Where: 1131 Kemper Hall
Title: Cloudy with a Chance of Leakage
The use of public cloud infrastructure for storing and processing data raises new challenges in terms of security. Current solutions propose encrypting all data, and accessing it in plaintext only within secure processors (e.g., Intel SGX). Nevertheless, processing large datasets requires these secure units to access shared memory and storage. Even if all their I/O are encrypted, the resulting access patterns may be observed by a prying eye, and leak information about private data being processed. To this end, algorithms operating on sensitive data have to be carefully designed and implemented to prevent the exploitation of any side channels induced by data-dependent access patterns.
In this talk, I will focus on a privacy-preserving multi-party machine learning service and techniques for protecting it against memory side-channel attacks. This service allows multiple organizations to perform collaborative data analytics while guaranteeing the privacy of their individual datasets. The framework relies on data-oblivious counterparts of several machine learning algorithms including decision trees and neural networks. Algorithmic techniques as well as platform specific hardware features are used to ensure that only public information, such as dataset size, is revealed. I will show that an efficient implementation of this framework on Intel Skylake processors scales up to realistic datasets, with overheads several orders of magnitude lower than with cryptographic-based approaches.
Bio: Olya Ohrimenko is a researcher in Constructive Security Group at Microsoft Research, Cambridge. Her research interests include data privacy, integrity and security issues that emerge in the cloud computing environment. She was a postdoctoral researcher at Microsoft Research in Cambridge and a research fellow at Darwin College, the University of Cambridge. Olya received her Ph.D. degree from Brown University in 2013 and a B.CS. (Hons) degree from the University of Melbourne in 2007. During her studies she was an intern at Google, Microsoft Research Redmond and IBM Research Zurich.
1131 Kemper Hall