Exhaustive Statistical Analysis for Detection of Metamorphic Malware

Abstract

Malware is a serious threat to the security of the system. With the widespread use of the World Wide Web, there has been a tremendous increase in virus attacks, making computer security an essential for every personal computer. The rat-race between virus writers and detectors has led to improved viruses and detection techniques. In recent years, metamorphic malwares have posed serious challenge to anti-virus writers. Current signature based detection techniques, heuristic based techniques are not comprehensive solutions. A formidable solution to detection of metamorphic malware is void. This paper investigates the problem of malware detection, specifically metamorphic malwares. The paper proposes a statistical based detection technique as a viable candidate for comprehensive detection of metamorphic malwares. Related work, experimental results and analysis of the results are presented in this paper.