A Universally Applicable Differential Privacy System: Redefining Utility in Database Privacy to Prioritize User Experience
Name
Xu-helenxu-meng-eecs-2022-thesis.pdf
Description
Thesis PDF
Size
492.55 KB
Format
Adobe PDF
Checksum (MD5)
1cdc76bfd66f63dd11bd2f57e9295076
Author(s)
Xu, Helen J.
Advisor(s)
Madden, Samuel
Cao, Lei
Date Issued
May 2022
Publisher
Massachusetts Institute of Technology
Abstract
Data privacy is a fundamental ethical goal. We must aim for innovating without exploiting. In order to provide formal privacy guarantees, differential privacy has been the central method of implementing database privacy. However, there are many barriers to widespread adoption. General methods lack accuracy and more innovative methods lack applicability beyond a specific kind of data or query. This project aims to create an effective differentially private system that provides an identical user experience to using raw data and redefines utility in database privacy to focus on the user experience.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
