Research Article
Detecting Cyber-Attacks on Wireless Mobile Networks Using Multicriterion Fuzzy Classifier with Genetic Attribute Selection
Table 6
The WPA2 per-class performance of the proposed method with and without attribute selection (approximated to three decimal digits).
| Normal/attack | Count | With attribute selection | Without attribute selection | Precision | Recall | | AUC | Precision | Recall | | AUC |
| Normal | 6000 | 0.906 | 0.935 | 0.920 | 0.916 | 0.906 | 0.970 | 0.937 | 0.961 | Fake AP | 1000 | 0.998 | 0.952 | 0.974 | 0.973 | 0.985 | 0.945 | 0.965 | 0.969 | Fake authentication | 1000 | 0.734 | 0.483 | 0.582 | 0.713 | 0.934 | 0.448 | 0.605 | 0.694 | Deauthentication | 1000 | 0.984 | 0.967 | 0.975 | 0.981 | 0.981 | 0.978 | 0.980 | 0988 | Syn flooding | 1000 | 0.822 | 0.997 | 0.901 | 0.998 | 0.874 | 0.997 | 0.931 | 0.998 |
|
|