BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.scipy.org//2023//speaker//FRA7AF
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20220710T000000
TZNAME:CDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T020000
RDATE:20231105T020000
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230312T030000
RDATE:20240310T030000
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:PPML: Machine Learning on data you cannot see - Valerio Maggio
DTSTART;TZID=America/Chicago:20230710T080000
DTEND;TZID=America/Chicago:20230710T120000
DTSTAMP:20261017T025245Z
UID:pretalx-2023-B9CHA7@cfp.scipy.org
DESCRIPTION:Privacy guarantee is **the** most crucial requirement when it 
 comes to analyse sensitive data. However\, data anonymisation techniques a
 lone do not always provide complete privacy protection\; moreover Machine 
 Learning models could also be exploited to _leak_ sensitive data when _att
 acked_\, and no counter-measure is applied. *Privacy-preserving machine le
 arning* (PPML) methods hold the promise to overcome all these issues\, all
 owing to train machine learning models with full privacy guarantees. In th
 is tutorial we will explore several methods for privacy-preserving data an
 alysis\, and how these techniques can be used to safely train ML models _w
 ithout_ actually seeing the data.
LOCATION:Classroom 203
URL:https://cfp.scipy.org/2023/talk/B9CHA7/
END:VEVENT
END:VCALENDAR