AndroTotal has simplified the process for getting an API Key. Login/Create an Account at http://andrototal.org/ and you will then be able to view your profile settings. There is an API Tab which contains your key.

This repository contains a set of scripts to automate the process of gathering data from malware samples, training a machine learning model on that data, and plotting its classification accuracy.

0. Make a copy of config-template.ini called config.ini and edit it.

1. Ensure that the "tools" subdirectory has been initialized ("$ git submodule update --init tools")

2. Either use get_samples.py to download samples or copy them into "all_apks" from another source. If you're using get_samples.py, you can monitor it in another shell by running watch "ls -l *.apk | wc -l"

3. sort_malicious.py uses andrototal.org to sort them into "malicious_apk" and "benign_apk" folders. You can monitor it in another shell by running watch "ls -l benign_apk/*.apk | wc -l && ls -l malicious_apk/*.apk | wc -l"

4. extract_apks_parallel.sh unpacks the .apk files into folders and processes some of the data therein. You can monitor it in another shell by running watch "wc -l benign_apk/valid_apks.txt; wc -l malicious_apk/valid_apks.txt"

5. Run one of the following scripts to generate feature vectors:

   • parse_xml.py for permissions. "app_permission_vectors.json" is generated
   • parse_maline_output.py for syscalls. "app_syscall_vectors.json" is generated. You will have to run maline first for this to work.
   • parse_disassembled.py for API calls. "app_method_vectors.json" is generated
   • parse_ssdeep.py for fuzzy hashes. "app_hash_vectors.json" is generated. You will have to run ssdeep first for this to work.
   • combine_features.py for a combination of the top weighted features. "app_feature_vectors.json" is generated. This only works if you've previously trained a network on the specified features, and the feature weights files are named appropriately.

6. Run $ run_trials.sh app_feature_vectors.json (or whichever json you want) which runs the tensorflow_learn.py script (where the ML happens) a number of times and puts the results into a folder. It also runs plot_data.py and match_features.py to create a plot and create a list of top weighted features, respectively.

7. Change the parameters or input data and repeat step 6. It should be non-destructive so you can compare the results of different runs.

Note: If you want to use a SVM instead of a neural network, use sklearn_svm.py in place of tensorflow_learn.py. You can also use sklearn_tree.py to use a decision tree.