Text Classification
Scikit-learn
Joblib
English
cybersecurity
penetration-testing
xgboost
enterprise
Instructions to use alirezaaminzadeh/pentestforge-severity-engine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use alirezaaminzadeh/pentestforge-severity-engine with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("alirezaaminzadeh/pentestforge-severity-engine", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
PentestForge Severity Engine
TF-IDF char n-gram + XGBoost multiclass classifier for penetration test finding severity prediction.
Intended Use
- Prioritize findings extracted from pentest reports
- Complement CVSS scores with ML-based severity classification
- CPU-friendly inference for SOC/GRC workflows
Training Data
- Synthetic anonymized findings
- mamtakumar/seven-phishing-email-datasets (mapped to finding records)
Limitations
- Not a substitute for human pentester judgment
- Trained on English technical text; Persian reports may have reduced accuracy
- Demo model โ retrain on your organization's finding taxonomy for production
Authors
Aria AI Red Team Engineering โ aria-ai.ir
- Downloads last month
- -