Malware Analysis and Classification using Artificial Neural Network

Today major and serious threat on internet is malicious software or data which damage the system. Malware variants identification and classification is the one of the most important research problem in digital forensics. Malware binaries are set of instructions which may affect your system without your authority. Many researchers worked in this area mainly relied on specific API calls, sequences of bytes, statistic and dynamic analysis is used for detection and classification of malware. The proposed method malware is represented as 2Dimensional gray scale image is observed malware images of all the available variants and their texture similarity, which motivate to classify malware based on texture features. The texture plays a very significant role in identify and classify malware. The objective of this paper is to identify a behavior of malicious data based on global features using Gabor wavelet transform and GIST. The experiment done on Mahenhur dataset which includes 3131 binaries samples comprising 24 unique malware families. The algorithm has been implemented using feed forward Artificial Neural Networks (ANN) it gives their overview uniqueness. The experimental results are promising to effectively detecting and classifying malware with good accuracy 96.35 %.