PE Files: Feature Engineering

In this project, you will take real-world PE file samples and featurize their PE header. The samples are available in this file:

 

featurizing-PE-samples-master

 

The malware samples are password protected with password “infected”. Make sure to exercise sound judgment and take safety precautions.

The features you will be extracting are:

  • The number of sections
  • The names of the sections
  • The names of the DLL imports

 

For example, the features of the first 5 files (sorted in alphabetical order by name) are:

 

Your solution should be a pandas DataFrame of the same format as the one shown above. Note that each feature is sorted in alphabetical order as well.

Leave a Reply