BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20221030T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20231029T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230326T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.25707.field_data.0@www.ugovricerca.uniroma1.it
DTSTAMP:20260404T185113Z
CREATED:20230511T164208Z
DESCRIPTION:The term “trustworthy AI” has become increasingly popular over 
 the last years – from academic research and publications\, lawmakers and r
 egulators\, to the press and the general public. In this course we have a 
 look at what dimensions are involved in making an AI system trustworthy\, 
 what are some of the scientific underpinnings and the current state of the
  art in the corresponding fields of academic and industry R&D\, and what a
 re the regulatory and market mechanisms which aim to make sure that end pr
 oducts indeed meet a certain (minimum) level of trustworthiness. We will v
 isit the foundations of the explainability and interpretability of AI syst
 ems\, of privacy-preservation\, of fairness/bias mitigation\, of security\
 , and of safety and discuss these from technological\, regulatory and soci
 etal perspectives. We will see that the concept of “trust” is multifaceted
  and spans across several criteria some of which may well be in conflict w
 ith each other\, requiring (ideally: conscious) tradeoffs between those mu
 tually not fully compatible aspects. Session 1 (9:00-10:30):Introduction t
 o Trustworthy AI – Mapping the LandscapeExplainability/InterpretabilityPri
 vacy-PreservationFairness/BiasSecuritySafetySession 2 (11:00-12:30):Trustw
 orthy AI – Regulation & Testing/CertificationThe EU AI ActThe Trustworthy 
 AI Framework of the EU HLEGAI StandardizationTesting/CertificationDiscussi
 on
DTSTART;TZID=Europe/Paris:20230512T090000
DTEND;TZID=Europe/Paris:20230512T090000
LAST-MODIFIED:20230512T070417Z
LOCATION:Aula A2
SUMMARY:Trustworthy AI - Tarek R. Besold (Sony AI)
URL;TYPE=URI:http://www.ugovricerca.uniroma1.it/node/25707
END:VEVENT
END:VCALENDAR