This repository contains all data and source code related to our research. The dataset presented in this repoitory is the result of preprocessing script presented in the src/preprocessing/preprocess_pcaps.py to the raw PCAP files provided by our colleagues from the Public University of Navarre [1].
## Repository Description
This repository contains all data and source code related to our research ```Unveiling Ransomware: Sequence Alignment and
Deep Learning for Early Detection```.
The repository consists of two parts. Directory ```sequences_dataset``` contains the raw data we performed our research on. This directory is further divided to ```ransomware``` and ```benign```.
The dataset presented in the ```ransomware``` directory is the result of preprocessing script presented in the ```src/preprocessing/preprocess_pcaps.py``` to the raw PCAP files provided by our colleagues from the Public University of Navarre [1]. For this reason we do not provide the raw PCAP files here.
The dataset presented in the ```benign``` directory contains the 5 benign use cases. We provide here both the raw PCAP files and the preprocessed flows. The PCAP files in this directory were taken from our lab and from the sample captures [2].
