An Automatic Unpacking Method for Computer Virus Effective in the Virus Filter Based on Paul Graham's Bayesian Theorem

Dengfeng ZHANG  Naoshi NAKAYA  Yuuji KOUI  Hitoaki YOSHIDA 

Publication
IEICE TRANSACTIONS on Communications  Vol.E92-B  No.4  pp.1119-1127
Publication Date: 2009/04/01
Online ISSN: 1745-1345
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Section on Internet Technology and its Architecture for Ambient Information Systems)
Category: 
Keyword: 
virus,  obfuscate,  compression,  unpacking,  Bayesian virus filter, 

Full Text: PDF(272.5KB)

Summary: 
Recently, the appearance frequency of computer virus variants has increased. Updates to virus information using the normal pattern matching method are increasingly unable to keep up with the speed at which viruses occur, since it takes time to extract the characteristic patterns for each virus. Therefore, a rapid, automatic virus detection algorithm using static code analysis is necessary. However, recent computer viruses are almost always compressed and obfuscated. It is difficult to determine the characteristics of the binary code from the obfuscated computer viruses. Therefore, this paper proposes a method that unpacks compressed computer viruses automatically independent of the compression format. The proposed method unpacks the common compression formats accurately 80% of the time, while unknown compression formats can also be unpacked. The proposed method is effective against unknown viruses by combining it with the existing known virus detection system like Paul Graham's Bayesian Virus Filter etc.