BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:7778-3492@fg-pet.gi.de
CLASS: PUBLIC
SUMMARY:PET Talk 9: Deployable Differential Privacy
DESCRIPTION:Differential privacy (DP) is a mathematical framework for prote
 cting individual privacy in computations on sensitive data. Despite robust 
 privacy guarantees and growing institutional support, DP has seen limited a
 doption. Research has identified multiple barriers, such as privacy risk as
 sessment challenges, utility concerns, and communication difficulties acros
 s diverse stakeholders. Overall, fewer than a dozen organizations have publ
 icly deployed DP, predominantly US government agencies and big tech compani
 es.  In his talk, Shlomi Hod will propose a vision for deployable different
 ial privacy, grounded in his own research and that of others. As the demand
  for "microdata format" releases increases, the talk will focus on differen
 tially private synthetic data. This vision will be demonstrated through a n
 ational birth registry release Shlomi leads, which represents the first dif
 ferentially private release of medical data, developed through a co-design 
 process with diverse stakeholders and which tackles these barriers. He'll c
 onclude the talk by presenting a future research agenda to advance the depl
 oyability of differential privacy.
LOCATION:Online
DTSTAMP:20260410T153154Z
DTSTART:20260428T140000Z
DTEND:20260428T150000Z
END:VEVENT
END:VCALENDAR