BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:MetaDroid: A Framework for Automatic Identification of Malicious 
 Applications Through App-Market Metadata - Ilias Leontiadis (University of
  Cambridge)
DTSTART:20121211T130000Z
DTEND:20121211T140000Z
UID:TALK41844@talks.cam.ac.uk
CONTACT:Ionel Gog
DESCRIPTION:The increasing popularity of modern smartphones can be\nlargel
 y attributed to the wide range of third-party mobile applications easily d
 ownloadable and installable through App-stores. However\, allowing users t
 o install third party applications also raises privacy and security concer
 ns: applications often ask for permissions that reveal private information
  such as the user's location\, contacts and messages without the actual ne
 ed for these data to be revealed to\nthe developers. Furthermore\, with th
 e number of available mobile applications growing\, so is the presence of 
 malicious applications which\, beyond data stealing\, could impact the use
 r's nances by for example sending text messages to premium rate numbers.\
 n\nWhile the detection of the maliciousness or the level of\noverprivilege
 d permission set of an application is possible through static or run-time 
 analysis of the application binaries\, techniques that are able to assess 
 the risks as soon as applications appear in the market are still lacking. 
 In this work\, we present an approach to the automatic detection of malici
 ous applications that solely exploits information included in the applicat
 ion roles and permission sets.\nWe devise a machine learning framework an
 d evaluate it\nusing two full snapshots of the Google Play store containin
 g more than 700\,000 applications\, as well as publicized datasets of mali
 cious applications discovered before October 2012. Our results indicate th
 at by examining the market meta-information we can automatically identify 
 up to 93% of possible threats as soon as they enter the market.
LOCATION:Computer Laboratory\, William Gates Building\, Room FW11
END:VEVENT
END:VCALENDAR