Details in blog post: https://blog.munhou.com/2020/04/06/Pytorch-Implementation-of-Deep-Packet-A-Novel-Approach-For-Encrypted-Tra%EF%AC%83c-Classi%EF%AC%81cation-Using-Deep-Learning/
- Clone the project
- Download the train and test set I created at here, or download the full dataset if you want to process the data from scratch.
- Run python codes with the docker image:
docker run -it \
-v /path/to/the/code:/data \
mhwong2007/deep_packet \
bash- If you want to run Jupyter notebook, use the following command:
docker run -it \
-v /path/to/the/code:/data \
-p 8888:8888 \
mhwong2007/deep_packet \
jupyter lab --no-browser --ip=0.0.0.0 --port=8888 --NotebookApp.token='' --allow-root- If you want to build the environment yourself, please install the dependencies and libraries in the Dockerfile
python preprocessing.py -s /path/to/CompletePcap/ -t processed_datapython create_train_test_set.py -s processed_data -t train_test_dataApplication Classification
python train_cnn.py -d train_test_data/application_classification/train.parquet -m model/application_classification.cnn.model -t appTraffic Classification
python train_cnn.py -d train_test_data/traffic_classification/train.parquet -m model/traffic_classification.cnn.model -t traffic
Download the pre-trained models here.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent