In this project, we describe the usage of available implementations of Perceptron and Random Forest from scikit-learn [1] for the Intrusion Detection problem, reproducing the results of tables 3 and 4 in [2], using Perceptron and Random Forest instead of Naive Bayes and Decision Tree, respectively. The data are sourced from the KDD Cup 1999 page [3], and additional dataset information is derived from [4].
To learn more: read the PDF in the repository.
In questo progetto si descrive l’utilizzo di implementazioni disponibili di Perceptron e Random Forest di scikit-learn [1] al problema dell’Intrusion Detection, riproducendo i risultati delle tabelle 3 e 4 presenti in [2], utilizzando rispettivamente Perceptron e Random Forest al posto di Naive Bayes e Decision Tree. I dati provengono dalla pagina della KDD Cup 1999 [3] e sono state tratte ulteriori informazioni sul dataset da [4].
Per saperne di più: leggi il pdf presente nella repo.
- F. Pedregosa and Varoquaux et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
- Amor et al. Naive bayes vs decision trees in intrusion detection systems. Proceedings of the ACM Symposium on Applied Computing, 2004.
- Irvine University of California. Kdd cup dataset. 1999. See: https://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html
- Mehdi Hosseinzadeh Aghdam and Peyman Kabiri. Feature selection for intrusion detection system using ant colony optimization. International Journal of Network Security, 2016.