"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
IDS Attack Detection with KDD99 & ML
1.
2. What is Intrusion Detection System
Attack Types
Problem Definition
KDDcup99
Reference Paper
3.
4.
5. Objective
Build a machine learning model/Deep learning model (classifiers) to detect the potential
attack type based on features in connections provided in the datasets.
Datasets: KDD cup 1999
https://www.kdd.org/kdd-cup/view/kdd-cup-1999/Data
8. Through this paper, the author compares various data pre-
processing methods categorized as:
1- Feature selection,
• Chi-Squared Test (CST)
• Random forest classifier (RFC)
• Extra tree classifier (ETC)
2- Feature encoding,
• One hot encoder (OHT)
• Binary encoder (BE)
• Frequency encoder (FE)
• Label encoder (LE)
3- and Feature scaling.
• Min-Max (MM)
• Standardization (Std)
• Binarizing(Bin)
• Normalizing(Norm)
The pre-processed data and an Autoencoder are used for
further processing to get the best features and use them with a
deep neural network for classification.