Usage of checkfile.py: python checkfile.py data/7f313447b887b078215617fbed1a34a1 Output: The file 7f313447b887b078215617fbed1a34a1 is malicious
Usage of model.py: Using the extracted out features csv, train the model. Each time run the model it will reproduce to a saved model and give you accuracy of different algo.
Usage of feature_extra.py: extract raw features from PE file.
Data: From ClaMP dataset features and I append extracted extra 100(some ruined so 89 actually) and two pe binary file, 1 good, 1 bad.
Pickle_saved: The saved feature selected and training result
Figures: As name indicated.
This is for security something awesome project. The old private repo was deprecated, this is a new repo just for submition. Working on private commits proof can be found in "2018-05-26 at 2.24.42 pm.png"