AI systems of every description are entering our lives to deliver ever more personalized assistance, medical care, and entertainment. The machine knows about you through your data, but does it know to protect your private information extracted from the data?

Learn about scenarios where privacy may leak, how naive privacy protection breaks, and how randomness can be leveraged to safeguard privacy through the advanced modern day paradigm of differential privacy. Xueji researches privacy preserving machine learning and its applications to healthcare AI systems, thinking deeply of ways for futuristic technologies to be trustworthy and private. This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at https://www.ted.com/tedx