See the SOSP'17 paper DeepXplore: Automated Whitebox Testing of Deep Learning Systems for more details.

The code should be run using python 2.7.12, Tensorflow 1.3.0, and Keras 2.0.8.

sudo pip install tensorflow

if you have gpu,

sudo pip install tensorflow-gpu

sudo pip install keras

Install from here.

• MNIST - MNIST dataset.
• ImageNet - ImageNet dataset.
• Driving - Udacity self-driving car dataset.
• PDF - Benign/malicious PDFs captured from VirusTotal/Contagio/Google provided by Mimicus.
• Drebin - Drebin Android malware dataset.

In every directory

python gen_diff.py

The trained weights are provided in each directory (if required). Drebin's weights are not part of this repo as they are too large to be hosted on GitHub. Download from here and put them in ./Drebin/.

How to test your own DNN models.