Abstract: Data scientists often struggle to acquire valuable datasets containing confidential data because of confidentiality concerns. The owners of the confidential datasets are often other teams in the same organization or other organizations. The owners often would like to enable the data scientists to compute statistics or train models on their confidential datasets, but are concerned about the data scientists or other parties seeing the contents of the datasets.
In this talk, I will describe our open-source platform MC2 (multi-party confidential computing) which enables data owners to encrypt their data and the data scientists to run analytics or machine learning on the encrypted data without having access to the data. MC2 is based on years of research at UC Berkeley and on publications at top tier security and privacy conferences.
Bio: Raluca Ada Popa is the Robert E. and Beverly A. Brooks associate professor of computer science at UC Berkeley working in computer security, systems, and applied cryptography. She is a co-founder and co-director of the RISELab and SkyLab at UC Berkeley, as well as a co-founder of Opaque Systems and PreVeil, two cybersecurity companies. Raluca has received her PhD in computer science as well as her Masters and two BS degrees, in computer science and in mathematics, from MIT. She is the recipient of the 2021 ACM Grace Murray Hopper Award, a Sloan Foundation Fellowship award, Jay Lepreau Best Paper Award at OSDI 2021, Distinguished Paper Award at IEEE Euro S&P 2022, Jim and Donna Gray Excellence in Undergraduate Teaching Award, NSF Career Award, Technology Review 35 Innovators under 35, Microsoft Faculty Fellowship, and a George M. Sprowls Award for best MIT CS doctoral thesis.