BEGIN:VCALENDAR
VERSION:2.0
PRODID:Departament d'Enginyeria Informàtica i Matemàtiques
BEGIN:VEVENT
UID:69fe830089759
DTSTART:20260610T100000Z
SEQUENCE:0
TRANSP:OPAQUE
DTEND:20260610T110000Z
URL:http://www.deim.urv.cat/ca/agenda-ca/12227/deiminari-synthetic-data-wit
 hout-the-hype-a-practical-playbook-for-privacy-risk-and-utility
LOCATION:Laboratori 231 DEIM
SUMMARY:DEIMinari: Synthetic Data Without the Hype: A Practical Playbook fo
 r Privacy\, Risk\, and Utility
CLASS:PUBLIC
DESCRIPTION:Títol:&nbsp\;Synthetic Data Without the Hype: A Practical Play
 book for Privacy\, Risk\, and Utility\n\nConferenciant: Dr. Khaled El Emam
  i Dr. Lisa Pilgram\n\nInstitució:&nbsp\;University of Ottawa\n\nProfesso
 r/a organitzador/a: Josep Domingo Ferrer\, Jesús A. Manjón Paniagua\n\nH
 ora: 12:00h\n\nResum:\n\nSynthetic data has emerged as a promising approac
 h to enable the sharing and reuse of data while mitigating privacy risks. 
 While synthetic data is often considered privacy-preserving by design\, re
 sidual vulnerabilities can persist\, for example\, when generative models 
 overfit to the training data. As a result\, important questions remain reg
 arding the extent to which synthetic data provides meaningful privacy prot
 ection\, as well as how to balance privacy with data quality and downstrea
 m utility.\nIn this talk\, we present recent work from our lab examining s
 ynthetic data as a privacy-enhancing technology. It draws on several years
  of applied research spanning regulatory expectations\, quantitative risk 
 assessment\, and practical considerations in synthetic data generation and
  evaluation.\nWe emphasize a risk-based perspective\, positioning syntheti
 c data not as inherently anonymous\, but as a technique that requires syst
 ematic evaluation to ensure both privacy protection and downstream utility
 . The talk concludes with a practical playbook for generating useful and p
 rivacy-preserving synthetic data
DTSTAMP:20260509T004240Z
END:VEVENT
END:VCALENDAR