BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Marginals and Malice - Cynthia Dwork (Microsoft (UK))
DTSTART:20160706T123000Z
DTEND:20160706T133000Z
UID:TALK66669@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span>In 2008 Homer et al rocked the genomics community with a
  discovery that altered the publication policies of the US NIH and the Wel
 lcome Trust\, showing that mere allele frequency statistics would permit a
  forensic analyst -- or a privacy attacker -- to determine the presence of
  an individual&#39\;s DNA in a forensic mix -- or a case group. &nbsp\;The
 se results were seen as particularly problematic for Genome-Wide Associati
 on Studies (GWAS)\, where the marginals are SNP minor allele frequency sta
 tistics (MAFs).<br> <br> In this talk\, we review the lessons of Homer et 
 al. and report on recent generalizations and strengthenings of the attack\
 , establishing the impossibility of privately reporting "too many" MAFs wi
 th any reasonable notion of accuracy. <br> <br> We then present a differen
 tially private approach to finding significant SNPs that controls the fals
 e discovery rate. &nbsp\;The apparent contradiction with the impossibility
  result is resolved by a relaxation of the problem\, in which we limit the
  total number of potentially significant SNPs that are reported. &nbsp\;<b
 r> <br> Joint work with Smith\, Steinke\, Ullman\, and Vadhan (lower bound
 s)\; and Su and Zhang (FDR control).<br> </span>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR