BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Machine Learning Approaches for Security Problems
DTSTART:20130314T161500
DTEND:20130314T173000
DTSTAMP:20260407T164019Z
UID:dedf29c3afad21d4503ba35e775d0e9716fc3e80c2d8605f4b290b67
CATEGORIES:Conferences - Seminars
DESCRIPTION:Mario Frank\, University of California Berkeley\nIC faculty ca
 ndidate\nAbstract\nFor many security problems it is increasingly difficult
  to manually examine the ever increasing amount of relevant data. At the s
 ame time\, noise in the data disqualifies deterministic automation approac
 hes. As a consequence\, the development of algorithms and systems that can
  learn and generalize from a large amount of noisy data constitutes one of
  the fastest growing fields of security.\nIn my talk I will outline this f
 ield and argue that it is an integral part of security. I will give exampl
 es of security problems where\, already today\, the best solutions involve
 \nunsupervised or supervised learning methods. My examples reach from loca
 l touch-based authentication for smart phones over mid-scale policy learni
 ng for enterprise systems to large-scale detection of malicious accounts i
 n online social networks. My talk highlights open problems that will guide
  my future research agenda.Biography\nMario Frank is currently a post-doct
 oral researcher in Dawn Song's group at the University of California\, Ber
 keley. Before joining UC Berkeley in 2011\, he was a PhD student at ETH Zu
 rich. His thesis ``Probabilistic Role Mining'' was awarded the ETH Medal. 
 Mario studied physics at the Ruprecht Karl University of Heidelberg and\nt
 he University of Sydney. In 2007\, he received the Otto-Haxel Preis for gr
 aduating best-of-class and for his diploma thesis about a 3D camera.\nHis 
 research interests lie in the intersection of security and machine learnin
 g.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR