Back to search

University of British Columbia

Dancing in the dark : private multi-party machine learning in an untrusted setting

Abstract

dc:description

The problem of machine learning (ML) over distributed data sources arises in a variety of domains. Unfortunately, today's distributed ML systems use an unsophisticated threat model: data sources must trust a central ML process. We propose a brokered learning abstraction that provides data sources with provable privacy guarantees while allowing them to contribute data towards a globally-learned model in an untrusted setting. We realize this abstraction by building on the state of the art in multi-party distributed ML and differential privacy methods to construct TorMentor, a system that is deployed as a hidden service over an anonymous communication protocol. We define a new threat model by characterizing, developing and evaluating new attacks in the brokered learning setting, along with effective defenses for these attacks. We show that TorMentor effectively protects data sources against known ML attacks while providing them with a tunable trade-off between model accuracy and privacy. We evaluate TorMentor with local and geo-distributed deployments on Azure. In an experiment with 200 clients and 14 megabytes of data per client our prototype trained a logistic regression model using stochastic gradient descent in 65 seconds.

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2018

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Fung, Clement

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/67623

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Fung, Clement. Dancing in the dark : private multi-party machine learning in an untrusted setting. master's thesis, University of British Columbia, 2018. http://hdl.handle.net/2429/67623