Classification of PE Files using Static Analysis

摘要: Malware is one of the most terrible and major security threats facing Internet today. Anti-malware vendors are challenged to identify, classify counter new malwares due obfuscation techniques being used by malware authors. In this paper, we present a simple, fast scalable method differentiating from cleanwares on basis features extracted Windows PE files. The in work Suspicious Section Count Function Call Frequency. After automatically extracting executables, use machine learning algorithms available WEKA library them into cleanwares. Our experimental results provide an accuracy over 98% for data set 3,087 executable files including 2,460 627 Based obtained, conclude that Frequency feature derived static analysis plays significant role distinguishing benign ones.