Binary Classification of Malwares from the Drebin dataset.
-
Create a raw_data folder inside the main directory of the repo.
-
Add the sha files and feature_vectors folder from this link https://drive.google.com/file/d/0Bxxqx_AAp2u2enI0UzBqSEZQRHc into the raw_data folder.
-
Create another folder titled "processed_data",inside the main directory of the repo. Don't put anything in here.
-
Run scripts/Malware_Classification_Model.py to extract and run the model with python3 or Malware_Classification_Model.ipnyb on Jupyter notebook
Random Forest Classifier:
Accuracy: 0.99
Precision: 0.98
Recall: 0.99
AUC: 0.99
Logistic Regression:
Accuracy: 0.82
Precision: 0.85
Recall: 0.78
AUC: 0.82