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:20231029T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20241027T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.28044.field_data.0@www.u-gov-ricerca.uniroma1.it
DTSTAMP:20260405T115600Z
CREATED:20240410T075853Z
DESCRIPTION:Abstract:Homomorphic encryption is a form of encryption that al
 lows specific mathematical operations to be performed on encrypted data wi
 thout decrypting it first. This capability is particularly significant in 
 the context of machine learning (ML) training\, where data privacy is a cr
 itical concern. By applying homomorphic encryption to ML training\, organi
 zations can harness the benefits of cloud-based computation while preservi
 ng the confidentiality of sensitive data.This abstract explores the concep
 t of homomorphic encryption and its application to machine learning traini
 ng. It begins by explaining the fundamental principles of homomorphic encr
 yption\, with practical examples implemented thrugh the Microsoft SEAL lib
 rary. The talk then discusses how homomorphic encryption addresses these c
 hallenges by allowing ML models to be trained directly on encrypted data. 
 This approach eliminates the need to share plaintext data with third-party
  service providers\, thus mitigating the risk of data breaches and unautho
 rized access. Speaker:Gaia Anastasi has a grant at the University of Pisa\
 , where she collaborates together with Prof. Gianluca Dini. Her research a
 ctivities focus on Homomorphic Encryption and its application to Machine L
 earning.
DTSTART;TZID=Europe/Paris:20240415T141500
DTEND;TZID=Europe/Paris:20240415T141500
LAST-MODIFIED:20240410T082103Z
LOCATION:Aula G50\, Dipartimento di Informatica
SUMMARY:'HE- based Privacy preserving training of ML models through Microso
 ft SEAL - Gaia Anastasi
URL;TYPE=URI:http://www.u-gov-ricerca.uniroma1.it/node/28044
END:VEVENT
END:VCALENDAR