/Malware-Visualization-and-Preprocessing-Methods-for-CNNs

Repository for Malware Visualization and Preprocessing work by Dr. Rakesh Verma and Alec Davila

Primary LanguagePythonMIT LicenseMIT

Malware-Visualization-and-Preprocessing-Methods-for-CNNs

Repository for Malware Visualization and Preprocessing work by Dr. Rakesh Verma and Alec Davila

Data Sets

Any data sets needed for this work should be placed in the data sets folder.

  /root/data-sets/

They will be ignored due to keeping the repository size as minimal as possible.

Data Sets used in evaluation:

  • MalImg Dataset orignally used in "Malware Images: Visualization and Automatic Classificatio"n by Nataraj et al., mentioned here. The link is currently dead and as of August 15, 2019 this link works.

  • Microsoft Malware Classification Challenge (BIG 2015): This is referenced in "Malware Classification with Deep Convolutional Neural Networks" by Kalash et. al.. The data set can be found from Kaggle

  • UH-JPL INSuRE (Spring 2019) dataset. Need to update a way to acquire the dataset.