IDS monitors a network or systems for malicious activity and protects a computer network from unauthorized access from users,including perhaps insider.
IDS monitors a network or systems for malicious activity and protects a computer network from unauthorized access from users,including perhaps insider.
The motive of this study is to propose a predictive model (i.e. a classifier) capable of distinguishing between 'bad connections' (intrusions/attacks) and a 'good
(normal) connections' after applying some feature extraction on KDD Cup 1999 dataset by DARPA.
DATASET
KDD Cup 1999 dataset by DARPA
The whole dataset can be downloaded from- http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html
MODELS
A total of seven models is trained and tested. The performance of all the algorithms is examined based
on accuracy and computational time. Derived results show that Decision Tree
outperforms the best on measures like Accuracy and Computational Time.
ALGORITHMS USED
Gaussian Naive Bayes, Decision Tree, Random Forest, SVM, Logistic Regression,Gradient Boosting, ANN
