Detection and Retrieval of Malware Using Classification
Aziz Makandar, Anita Patrot · 2017
This article a model of detection of malware classification is build using image processing techniques. In that image similarity approach is used to detect and retrieve of viruses in the form of malwares. Experimental result analysis done on Malimg data set for experiments and show that using image processing techniques such as Normalization of malware gray scale images then apply wavelet transform using Discrete Wavelet Transform at three level decomposition with PCA. The dimensionality reduction is done on normalized image such as preprocessed malware. After decomposition we apply wavelet based on Statistical Features (SF) such as mean, RMS, Standard Deviation & Variance. This model produces the TP (True Positive) and FP (False Positive) that are used to measures results for Image matching based malware detection framework. The proposed algorithm gives 92.92% accuracy and 92.38 %precision on Mahenuer dataset, and also on 88.75% accuracy and 90.15% precision on Malimg dataset.