Confidential and Private Collaborative Machine Learning
Adam Dziedzic
The Vector Institute & University of Toronto
CIS@MPG Colloquium
Adam Dziedzic is a Postdoctoral Fellow at the Vector Institute and the University of Toronto, advised by Prof. Nicolas Papernot, where he is working on trustworthy ML. Adam finished his Ph.D. at the University of Chicago, advised by Prof. Sanjay Krishnan, where he worked on input and model compression for adaptive and robust neural networks. He obtained his Bachelor's and Master's degrees from Warsaw University of Technology. Adam was also studying at DTU and EPFL. He worked at CERN, Barclays Investment Bank, Microsoft Research, and Google.
This talk outlines my work building systems that enable applications to securely interact with users' data while preserving individuals' privacy. First, I'll talk bout how we can bring the power of secure computation to difficult settings: TimeCrypt is an encrypted time-series database design that meets the scalability and low-latency requirements associated with time-series workloads. Then, I'll discuss work on using end-to-end privacy as a strong foundation for data protection: Zeph is a new end-to-end privacy system that provides the means to extract value from encrypted streaming data safely while ensuring data confidentiality and privacy by serving only privacy-compliant views of the data. Throughout the talk, I will discuss the prevalent challenges of efficiency, functionality, and accessibility in this research area; my approach to addressing these challenges; and future directions that will help bring end-to-end privacy to an even wider range of applications.
Please contact MPI-SWS Office Team for link information