| Title | Malware Classification Using Recurrence Plots and Deep Neural Network |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Sartoli, Sara, Wei, Yong, Hampton, Shane |
| Conference Name | 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA) |
| Date Published | dec |
| Keywords | convolutional neural networks, Deep Learning, Human Behavior, Malware, malware classication, malware classification, Metrics, privacy, Programming, pubcrawl, Recurrence Plots, resilience, Resiliency, static analysis, Task Analysis, transfer learning, Transforms, visualization |
| Abstract | In this paper, we introduce a method for visualizing and classifying malware binaries. A malware binary consists of a series of data points of compiled machine codes that represent programming components. The occurrence and recurrence behavior of these components is determined by the common tasks malware samples in a particular family carry out. Thus, we view a malware binary as a series of emissions generated by an underlying stochastic process and use recurrence plots to transform malware binaries into two-dimensional texture images. We observe that recurrence plot-based malware images have significant visual similarities within the same family and are different from samples in other families. We apply deep CNN classifiers to classify malware samples. The proposed approach does not require creating malware signature or manual feature engineering. Our preliminary experimental results show that the proposed malware representation leads to a higher and more stable accuracy in comparison to directly transforming malware binaries to gray-scale images. |
| DOI | 10.1109/ICMLA51294.2020.00147 |
| Citation Key | sartoli_malware_2020 |
Malware Classification Using Recurrence Plots and Deep Neural Network