Back to search

University of Waterloo

Evolving Trade-offs Towards Deployable Private Systems for Data Science

Abstract

dc:description.abstract

There is no one-size-fits-all solution to preserving privacy in data science. While insights derived from sensitive data can benefit society, privacy is typically at odds with utility, performance, usability, or some combination of these objectives. Furthermore, each system differs in its definition of these objectives and the way they interact with one another. If the compromise required for any single objective is too great, the system will not be deployed, or worse, will be deployed with a weakened privacy guarantee, exposing users to potential harm. In this work, we address this challenge from multiple angles. First, through strategic algorithm design, our work creates private systems with improved trade-offs, enabling their deployment. This includes a more efficient protocol for the secure inference of deep machine learning models, a novel construction for aggregating key-value data in the local trust model, an evolutionary approach to improve the utility of private clustering, and a user-friendly interpretation of the error of private median queries. Second, we audit private systems to show the privacy risks associated with misleading privacy claims. In particular, through a privacy audit of machine learning, we highlight a difference between expectation and reality in privacy protections.

Degree

thesis:*
Grantor dc:publisher
University of Waterloo
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Humphries, Thomas

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/10012/23930

Chain of custody

source
Harvested from
University of Waterloo
Base URL
dspacemainprd01.lib.uwaterloo.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Humphries, Thomas. Evolving Trade-offs Towards Deployable Private Systems for Data Science. University of Waterloo, 2026. https://hdl.handle.net/10012/23930