Skip to main content

Table 25 Summary of ML for Hybrid Intrusion Detection

From: A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Ref.

ML Technique

Dataset

Features

Evaluation

    

Settings

Results

Mukkamala et al. [325]

Supervised RBF-SVM (Online)

KDD cup [257]

all 41 features

7,312 training records -6,980 testing records -Platform used: SVMLight [224]

Accuracy: 99.5% Training time: 17.77 sec Testing Time: 1.63 sec

Zhang et al. [494]

Hybrid Hierarchical-RBF (Online)

KDD Cup

all 41 features

-32,000 training records -32,000 testing records

SHIDS Normal DR:=99.5%

     

SHIDS Normal FP: 1.2%

     

SHIDS Attack DR: [98.2%-99.3%]

     

SHIDS Attack FP: [0%-5.4%]

     

PHIDS level 1 DR: 99.8%

     

PHIDS level 1 DR:1.2%

     

PHIDS level 2 DR:[98.8%-99.7%]

     

PHIDS level 2 FP:[0%-4%]

     

PHIDS level 3 DR: 86.9%

     

PHIDS level 3 FP: 0%

     

Training time: 5 min

Depren et al. [116]

Hybrid SOM w./ J.48 (Offline)

KDD Cup

6 basic features for SOM all 41 features for J.48

-10-fold cross validation -Two-phases SOM Training -Phase 1 learning rate:0.6 -Phase 2 learning rate: 0.05 -Confidence Val. for J.48 pruning: 25%

DR: 99.9% Missed Rate: 0.1% FP: 1.25%