Date of Award

2-2019

Type

Thesis

Major

Master of Science

Degree Type

Master of Science

Department

TSYS School of Computer Science

First Advisor

Alfredo Perez

Second Advisor

Yesem Peker

Third Advisor

Lydia Ray

Abstract

Through the increasingly common use of devices that provide ubiquitous sensor data such as wearables, mobile phones, and Internet-connected devices of the sort, privacy challenges are becoming even more significant. One major challenge that requires more focus is bystanders' privacy, as there are too few solutions that solve the issue. Of the solutions available, many of them do not give bystanders a choice in how their private data is used, Bystanders' privacy has become an afterthought when it comes to data capture in the forms of photographs, videos, voice recordings, etc. and continues to remain that way. This thesis provides a solution to enhance bystanders' facial privacy by developing a wearable device called FacePET that provides a way for bystanders to protect their privacy and give consent. FacePET was evaluated using experiments to detect faces in photos when users wore the device and by performing a usability study with 21 participants. We found that FacePET was successfully able to block 15 of the 21 participants' faces, yielding a success percentage of 71%. We found through the usability study that a majority of the participants would be willing to use FacePET, or a similar device, daily for their facial privacy protection.

Share

COinS