BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Helen: Maliciously Secure Coopetitive Learning for Linear Models
DTSTART:20190620T101500
DTSTAMP:20260407T195035Z
UID:d01c2edab0239051f4e50c26ee6d7994a4ac4e4faabae7891ad968be
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Raluca Popa\nAbstract\nMany organizations wish to collab
 oratively train machine learning models on their combined datasets for a c
 ommon benefit (e.g.\, better medical research\, or fraud detection). Howev
 er\, they often cannot share their plaintext datasets due to privacy conce
 rns and/or business competition. In this talk\, I will present Helen\, a s
 ystem that allows multiple parties to train a linear model without reveali
 ng their data\, a setting we call coopetitive learning. Compared to prior 
 secure training systems\, Helen protects against a much stronger adversary
  who is malicious and can compromise m − 1 out of m parties. Our evaluat
 ion shows that Helen can achieve up to five orders of magnitude of perform
 ance improvement when compared to training using an existing state-of-the-
 art secure multi-party computation framework. \nJoint work with Wenting Z
 heng\, Joey Gonzalez and Ion Stoica.\n \nBiography\nRaluca Ada Popa is an
  assistant professor of computer science at UC Berkeley working in compute
 r security\, systems\, and applied cryptography. She is a co-founder and c
 o-director of the RISELab at UC Berkeley\, as well as a co-founder and CTO
  of a cybersecurity startup called PreVeil. 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 a Sloan Fou
 ndation Fellowship award\, Microsoft Research Faculty Fellowship\, Hellman
  Faculty Award\, an Intel Early Career Faculty Honor award\, George M. Spr
 owls Award for best MIT CS doctoral thesis\, and a Johnson award for best 
 CS Masters of Engineering thesis from MIT.\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR