A Detection of Malicious Code Based on Minimum Distance Classifier
Lei Liu · Journal of Guangxi Normal University · 2009
Malicious code is a new breed of Internet threat that cannot be efficiently controlled by conventional antivirus software alone.The increasing rate of the unknown malicious code is the growth of geometric times,and the preventing measure is manual analysis by signature,which is limited.The paper expounds an unknown malicious code detection based on minimum distance classifier,which has the capacity to distinguish malicious code and reliable programs.The customize host behaviors modeling classifier is used and the experiment indicated that it the time complexity of minimum distance classifier had been less than non-linear model,had excellent classify capacity,and which has the practical value in antivirus process.