| Popis: |
Threats derived from Internet of Things (IoT) malicious software are fast progressing and difficult phenomena. Contrary to conventional networks, Internet of things has unique attributes like non compatibility of devices, elevated scalability and different architectures that makes its malware analysis difficult. In this paper, we have developed a new method to analyzing and classifying IoT malware using decomposition image based on the Partial Differential Equations (PDE), the effective texture features extraction is performed not on the original image but on its texture component obtained by the PDE. The texture features based on Haralick are then calculated, and machine learning classifiers namely K-nearest neighbor (KNN), naive Bayes (NB) and random forest (RF) are used. A binary file (malicious or benign) is transformed to a gray scale image. The gray level co-occurence matrix (GLCM) is computed not on the original image but on its texture component. |
