BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20231215T021214Z
UID:567FBD08-1E0C-400E-B3FA-A7A6BFB9C2FC
DTSTART;TZID=America/New_York:20231106T130000
DTEND;TZID=America/New_York:20231106T140000
DESCRIPTION:Federated Learning (FL) has emerged as a promising large-scale 
 collaborative learning framework for its potential to protect user privacy
  and security. However\, this promise has been constantly challenged. In t
 his talk\, we show that FL in its primitive form offers little to no priva
 cy and security protection\, by analyzing several attack vectors\, both fr
 om malicious users to a dishonest server. Even with a layer of protection 
 from differential privacy and secure aggregation\, we further demonstrate 
 that current FL implementation provides no guarantee on privacy and securi
 ty\, thus calling for a fundamental re-design.\n\nCo-sponsored by: Dept of
  Electrical Engineering and Computer Science\, Florida Atlantic University
 \, Boca Raton\, FL 33431\n\nSpeaker(s): Dr. My Thai\, \n\nRoom: 405\, Bldg
 : EE96 -- Engineering East\, Florida Atlantic University\, Boca Raton\, Fl
 orida\, United States\, 33431\, Virtual: https://events.vtools.ieee.org/m/
 380993
LOCATION:Room: 405\, Bldg: EE96 -- Engineering East\, Florida Atlantic Univ
 ersity\, Boca Raton\, Florida\, United States\, 33431\, Virtual: https://e
 vents.vtools.ieee.org/m/380993
ORGANIZER:hkalva@fau.edu
SEQUENCE:23
SUMMARY:Federated Learning: Big Promise or False Hope? - Dr. Thai
URL;VALUE=URI:https://events.vtools.ieee.org/m/380993
X-ALT-DESC:Description: <br /><p>Federated Learning (FL) has emerged as a p
 romising large-scale collaborative learning framework for its potential to
  protect user privacy and security. However\, this promise has been consta
 ntly challenged. In this talk\, we show that FL in its primitive form offe
 rs little to no privacy and security protection\, by analyzing several att
 ack vectors\, both from malicious users to a dishonest server. Even with a
  layer of protection from differential privacy and secure aggregation\, we
  further demonstrate that current FL implementation provides no guarantee 
 on privacy and security\, thus calling for a fundamental re-design.&nbsp\;
 </p>
END:VEVENT
END:VCALENDAR