BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Extracting the Semantic Signature of Malware\, Metamorphic Viruses
  and Worms - RK Shyamasundar\; Tata Institute of Fundamental Research\, Mu
 mbai
DTSTART:20101008T130000Z
DTEND:20101008T140000Z
UID:TALK27094@talks.cam.ac.uk
CONTACT:Alan Mycroft
DESCRIPTION:[Shyam is visiting the CL until 14 October 2010.]\n\nMalware i
 s increasingly becoming a serious threat and a nuisance in the information
  and network age. Human experts extract (involves complex analysis of encr
 ypted and/or packed binaries) a signature (usually a text pattern) of the 
 malware and deploy it\, to protect against a malware.\n\nHowever\, this ap
 proach does not work for polymorphic and metamorphic malware\, which have 
 the ability to change shape from attack to attack\; also\, metamorphic vir
 us detection (even assuming fixed length) is NP-complete. To\ncounter thes
 e advanced forms of malware we need semantic signatures which capture the 
 essential behaviour of the malware (which remains unchanged across variant
 s).\nIn this talk\, we present an algorithmic approach for extracting the 
 semantic signature of a malware -- as a regular expression over API calls 
 -- and demonstrate via experiments its efficacy in detecting and predictin
 g malware variants. Our approach involves two steps. In the first step\, w
 e collect and abstract the behaviour (as a sequence of security relevant A
 PI/system calls)\nof the malware in different runs. In the second step\, w
 e inductively learn (under the supervision of a human expert) a regular ex
 pression that tightly fits these behaviours (generalizing where necessary)
 . This regular expression then acts as the semantic signature of the malwa
 re. We performed experiments with the metamorphic virus Etap/Simile\, and 
 the email worms Beagle\, Netsky and MyDoom.\n\nExperimental results give u
 s a good confidence\nthat our approach can be effectively used for malware
  detection.
LOCATION:FW11\, Computer Laboratory
END:VEVENT
END:VCALENDAR
