In this talk I will focus on two topics that I am currently doing research on: privacy-preserving machine learning and blockchain technologies.
With success stories ranging from online matchmaking to self-driving cars, machine learning has been one of the most impactful areas of computer science. Machine learning’s versatility stems from the wealth of techniques it offers, making machine learning seem to have a tool for any task that involves building a model from data. And yet, machine learning makes an implicit overarching assumption that severely limits its applicability to a broad class of critical domains: the data owner is willing to disclose the data to the model builder. However, in many industries, the diverse players cannot or will not share their data due to economic incentives or privacy legislation. The ultimate example of such privacy-sensitive domains is the healthcare industry. This state of affairs creates a dire need for privacy-preserving machine learning techniques, and despite prior research in the area, cryptographically secure machine learning is still in its infancy. My research goal is the development of a scalable framework for privacy-preserving machine learning.
On the topic of blockchains technologies, my goal is providing formal security guarantees for these technologies and their applications. One focus of my research in this area is on using smart contracts for obtaining practical distributed protocols that enforce fairness.