https://github.com/bcebere/guidelines-for-dga-based-malware-detection

Reference models and benchmarks for DGA generation and detection
https://github.com/bcebere/guidelines-for-dga-based-malware-detection

dga-detection domain-generation-algorithm machine-learning machine-learning-algorithms

Last synced: about 1 month ago
JSON representation

Reference models and benchmarks for DGA generation and detection

• Host: GitHub
• URL: https://github.com/bcebere/guidelines-for-dga-based-malware-detection
• Owner: bcebere
• License: gpl-3.0
• Created: 2024-03-20T12:02:18.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-07-18T09:57:33.000Z (5 months ago)
• Last Synced: 2024-10-12T18:56:44.292Z (2 months ago)
• Topics: dga-detection, domain-generation-algorithm, machine-learning, machine-learning-algorithms
• Language: Python
• Homepage:
• Size: 271 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Guidelines for DGA-based Malware Detection

In this repository, we provide the code to reproduce the results in the "Down to earth! Guidelines for DGA-based Malware Detection" paper.

![distributions_tsne_dga](https://github.com/bcebere/Guidelines-for-DGA-based-Malware-Detection/assets/1623754/4af8040f-9e7f-4994-80ac-fb1f784dba96)

## Repository structure

This repository is organized as follows:

```bash

src/

    |- dga_analysis/                        # Library containing models and benchmarks

      |- datasets/                          # Dataloaders for benign and DGA datasets

      |- detection/                         # Reference detection models

      |- generators/                        # Custom generators models

      |- utils/                             # Statistical and benchmarking tools

experiments/                                # Scripts and notebooks for generating the results in the paper

tests/                                      # Library unit tests

```

## Install

``` Bash

pip install -e .

pip install -e .[testing] # for the development setup

```

## Get the datasets

Review the docs [here](src/dga_analysis/datasets/.data/README.md) and create the local datasets

## Run the tests

If everything is fine, most of the tests should pass

```bash

pytest -vvsx

```

## Citing

If you use this code, please cite the associated paper:

```

@inproceedings{cebere2024guidelines,

  title={Down to earth! Guidelines for DGA-based Malware Detection},

  author={Cebere, Bogdan and Flueren, Jonathan and Sebastián, Silvia and Plohmann, Daniel and Rossow, Christian},

  booktitle={Proceedings of the 27th International Symposium on Research in Attacks, Intrusions and Defenses},

  year={2024}

}

```