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

Phadke, Nishad Ashok

Permalink

https://hdl.handle.net/2142/99116 Copy

Description

Title

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

Author(s)

Phadke, Nishad Ashok

Issue Date

2017-07-18

Director of Research (if dissertation) or Advisor (if thesis)

Vaidya, Nitin H.

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Distributed optimization
• Privacy

Abstract

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.

Graduation Semester

2017-08

Type of Resource

text

Permalink

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

Copyright and License Information

Copyright 2017 Nishad Phadke

Owning Collections