A framework for privacy-preserving, distributed machine learning using gradient obfuscation

Large-scale machine learning has recently risen to prominence in settings of both industry and academia, driven by today's newfound accessibility to data-collecting sensors and high-volume data storage devices. The advent of these capabilities in industry, however, has raised questions about the privacy implications of new massively data-driven, subscribable services offered by corporations to individuals. Recent lines of research have developed algorithms designed to scale in distributed machine learning environments that make certain privacy guarantees to subscribers without hindering the quality of service the corporations are able to provide. In this work, we fully implement one such distributed optimization framework and rigorously test its parameterized convergence properties. We also develop a system of both disruptive and nondisruptive attacks designed to aggressively intrude upon subscribers' privacy and to glean subscribers' private data from information readily available within the framework's network. These attack techniques can be seamlessly integrated into the aforementioned distributed optimization framework and are shown to be a risk to the privacy of the system.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2018

Author dc:creator

• Phadke, Nishad Ashok

Contributors dc:contributor

• Vaidya, Nitin H.

• Distributed optimization
• Privacy

Statement dc:rights

• Copyright 2017 Nishad Phadke

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/99116

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F99116