Identification Of Malware Using Enhanced Malware Detection Pre-Processing Techniques

Abstract

This research paper proposes a machine learning based malware analysis framework, which is made out of three modules: data processing, decision making, and new malware detection. The data processing module manages text to ASM, Opcode n-gram, and import functions, which are utilized to remove the features of the malware. The decision-making module utilizes the features to group the malware and to identify suspicious malware. Malware designers have been profoundly fruitful in evading the signature based detection techniques. The greater part of the prevailing static analysis techniques involve an instrument to parse the document. The entire analysis process gets dependent to the efficiency of the instrument; if the device crashes the procedure is hampered. The greater part of the dynamic analysis techniques involve the binary document to be run in a sand-boxed environment to examine its behaviour. This can be handily upset by hiding the malicious activities of the _le on the off chance that it is being run inside a virtual environment.