BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Reconciling Data Science with Privacy: The Case of Biomedical Data
DTSTART:20161216T133000
DTEND:20161216T143000
DTSTAMP:20260611T010151Z
UID:582699b6acf0188f4eb1e5350915b0a050528932e6d48a964d338a01
CATEGORIES:Conferences - Seminars
DESCRIPTION:Abstract: The increasing availability of biomedical data brin
 gs great promises for the future of healthcare\, enabling a more precise\,
  preventive and personalized medicine. However\, such availability and us
 age of very sensitive data also raises new concerns about privacy. In this
  talk\, I will first provide some background on the various types of biome
 dical data in the human biological “OSI stack”. I will then present ma
 chine-learning models to precisely quantify privacy risks at three differe
 nt layers of the biological stack. Moreover\, I will introduce various tec
 hnical means\, including differential privacy and encryption\, to enhance 
 privacy without reducing too much the utility of machine-learning algorith
 ms. Finally\, I will show how the models and methods developed for health 
 data privacy can be applied to other contexts\, such as mobility and locat
 ion data.\nBiography: Mathias Humbert is a post-doctoral researcher in the
  Center for IT-Security\, Privacy\, and Accountability (CISPA) at Saarland
  University\, Germany. He completed his Ph.D. thesis on interdependent pri
 vacy in March 2015\, under the supervision of Jean-Pierre Hubaux\, in the 
 School of Computer and Communication Sciences at EPFL. Prior to this\, he 
 earned his M.Sc. (2009) and B.Sc. (2007) degrees from EPFL\, and studied f
 or one year (2007-2008) at UC Berkeley. His current research interests lie
  at the intersection of security and machine leaning\, with a special focu
 s on bioinformatics.\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR