BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Private Data Analysis over Large Populations - Professor Graham Co
 rmode - Research Scientist\, Facebook and professor in the Department of C
 omputer Science\, University of Warwick
DTSTART:20240313T150500Z
DTEND:20240313T155500Z
UID:TALK209983@talks.cam.ac.uk
CONTACT:Ben Karniely
DESCRIPTION:Many applications in modern computing (AI\, ML and data scienc
 e) rely on the data from many individuals.  However\, this data is often s
 ensitive\, and needs to be handled under strong guarantees of privacy and 
 security. \n  I'll discuss a range of approaches that can be used at scale
  to gather statistics and build models of data while ensuring the strong g
 uarantees are met.  These combine techniques from differential privacy\, f
 ederated learning\, and cryptography.\n\n\nLink to join virtually: https:/
 /cam-ac-uk.zoom.us/j/81322468305\n\nA recording of this talk is available 
 to members of the University at the following link: https://www.cl.cam.ac.
 uk/seminars/wednesday/video/
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR