https://github.com/marcoramilli/MalwareTrainingSets

Free Malware Training Datasets for Machine Learning
https://github.com/marcoramilli/MalwareTrainingSets

machine-learning malware malware-analysis training-set

Last synced: 2 months ago
JSON representation

Free Malware Training Datasets for Machine Learning

• Host: GitHub
• URL: https://github.com/marcoramilli/MalwareTrainingSets
• Owner: marcoramilli
• Created: 2016-12-11T18:11:55.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2021-01-03T20:58:37.000Z (over 3 years ago)
• Last Synced: 2024-01-26T00:39:39.750Z (5 months ago)
• Topics: machine-learning, malware, malware-analysis, training-set
• Language: Python
• Size: 49.2 MB
• Stars: 208
• Watchers: 13
• Forks: 101
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml

Lists

• awesome-ml-for-cybersecurity - Malware Training Data Sets
• awesome-ml-for-cybersecurity - Malware Training Data Sets
• awesome-ml-for-cybersecurity - Malware Training Data Sets
• awesome-ml-for-cybersecurity - Malware Training Data Sets
• awesome-ml-for-cybersecurity - Malware Training Data Sets
• Awesome-ML-Cybersecurity - Malware training data set

README

        
# MalwareTrainingSets

Please check it out: https://marcoramilli.com/2016/12/16/malware-training-sets-a-machine-learning-dataset-for-everyone/

For an updated followUP please check it out: https://marcoramilli.com/2019/05/14/malware-training-sets-followup/

**Cite The DataSet**  

If you find those results useful please cite them :

    

    

    @misc{ MR,

       author = "Marco Ramilli",

       title = "Malware Training Sets: a machine learning dataset for everyone",

       year = "2016",

       url = "https://marcoramilli.com/2016/12/16/malware-training-sets-a-machine-learning-dataset-for-everyone/",

       note = "[Online; December 2016]"

     }

*UPDATE*

Many people asked me about the scripts I used to generate MIST-Modified JSON. So here there are ! (take a look to scripts section).

You might use `mist_json.py`  as a reporting module from CuckooSandbox and the script `fromMongoToARFF.py` to generate ARFF files suitables for WEKA.

If you are going to create new datasets by running your local CuckooSandbox using `mist_json.py` module and you wanto to share them, please feel free to make pool requests !

If you want to know more about the working flow, please check this update: https://marcoramilli.com/2019/05/14/malware-training-sets-followup/