Privacy-Preserving Machine Learning: Protecting User Data in AI Systems; Understanding Privacy Concerns in the Rise of Wearable Healthcare Devices

Data privacy is a big concern in today’s world. Many companies and organizations collect data from users every day. This is especially true in healthcare, where patient information is very sensitive. Protecting this data is important because it can affect people’s lives. What I worked on focused on this big problem of data privacy. Both of my projects looked at how to keep data safe while still using technology in helpful ways. My technical report for CS4991 focused on privacy-preserving machine learning. This is a way to train smart models without collecting people’s private data in one place. My STS research paper looked at a more specific case which included wearable devices in hospitals. These are devices like smartwatches or fitness trackers that collect health data from patients. While these devices can help doctors, they also bring up privacy concerns. People worry about who is seeing their data or how it’s being shared. Both of my projects deal with this same issue of privacy, but from different angles. One is more technical, and one is about real-world healthcare settings. Together, these projects show how important it is to protect people’s information while still using technology to help them.

School of Engineering and Applied Science

Bachelor of Science in Computer Science

Technical Advisor: Rosanne Vrugtman

STS Advisor: Kent Wayland