This repository contains the code of the paper MAppGraph: Mobile-App Classification on Encrypted Network Traffic using Deep Graph Convolution Neural Networks. Please cite MAppGraph when using it in academic publications.

MAppGraph introduces a method for processing network traffic and generating graphs with node features and edge weights that better represent the communication behavior of mobile apps. A Deep Graph Convolution Neural Network (DGCNN) model has been designed and developed to learn the communication behavior of mobile apps from a large number of graphs, thus being able to classify mobile apps.

We provide an extensive documentation including instructions for running the code at MAppGraph.

Thai-Dien Pham, Thien-Lac Ho, Tram Truong-Huu, Tien-Dung Cao, Hong-Linh Truong, “MAppGraph: Mobile-App Classification on Encrypted Network Traffic using Deep Graph Convolution Neural Networks”, Annual Computer Security Applications Conference - ACSAC, December 6-10, 2021.

@INPROCEEDINGS{MAppGraph2021,
  author={Pham, Thai-Dien and Ho, Thien-Lac and Truong-Huu, Tram and Cao, Tien-Dung and Truong, Hong-Linh},
  booktitle={Annual Computer Security Applications Conference (ACSAC 2021)}, 
  title={{MAppGraph: Mobile-App Classification on Encrypted Network Traffic using Deep Graph Convolution Neural Networks}}, 
  year={2021},
  month = {December},
  address={Virtual Conference}
}