Princeton University

School of Engineering & Applied Science

Privacy-Preserving Machine Learning via Data Compression & Differential Privacy

Speaker: 
Thee Chanyaswad
Advisor: 
SY Kung and Prateek Mittal
Location: 
J401, E-Quad
Date/Time: 
Wednesday, October 10, 2018 - 4:00pm to 5:00pm

In the current world of ubiquitous information, data have been generated and used to improve our daily living in many aspects such as image recognition, speech recognition, and medical diagnosis. The successful utilization of the data can largely be attributed to the development in machine learning. Despite the benefits provided by machine learning, the ubiquitous nature of the data comes with an important concern, i.e. the privacy of the individuals to whom the data are associated. While machine learning tries to learn as much as possible from the data, the privacy concern results in the desire to conceal as much information as possible. Therefore, the intersection between the two is inevitable. 

The body of work presented in this dissertation explores this intersection between data privacy and machine learning using knowledge, theories, and techniques from many related fields including statistics, linear systems theory, information theory, probability theory, and signal processing. The results have spawned many exciting directions for future research and deployment of privacy-preserving machine learning systems.

Lastly, despite its rapid development in recent years, privacy-preserving machine learning is possibly still in its infant stage compared to other fields. Nevertheless, its importance cannot be understated, and future works in the area would certainly have a meaningful impact on our quality of life in this evermore technologically-oriented world.