ANALYSIS OF RESNET MODEL FOR MALICIOUS CODE DETECTION

In this study, we have used the ResNet model to detect the new type of malware. ResNet model is investigated and tested which belongs to Microsoft. We have used two types of datasets to train and test the model. We collected dataset from Microsoft Malware Classification Challenge which contains 10868 Binary files, these binary files are further divided in nine different malware families and second dataset is benign dataset which contained 3000 different kinds of benign software. Benign dataset and dataset from Microsoft Malware Classification Challenge were initially. exe files which were converted in to opcode and then converted in to image files. We obtained a testing accuracy of 87.98% on ResNet model.