Feature Selection in Wireless Intrusion Detection System for Evil Twin Attack Detection
Abhijit Kamble, Deepak D. Kshirsagar · 2023
Wireless networks have become an integral part of our daily lives, enabling seamless communication and information exchange. Attackers continuously seek vulnerabilities in these networks to compromise data privacy and integrity. To address the growing threat of evil twin attacks and other wireless network vulnerabilities, Wireless Intrusion Detection Systems (WIDS) play a vital role in detecting suspicious activities. However, implementing WIDS poses challenges due to the large amount of network data generated, which can strain detection mechanisms and lead to delays or false positives. To mitigate this, feature selection techniques are employed to identify relevant features that optimize detection while reducing processing overhead. This article proposes a framework for WIDS using Random Forest classifiers and Gini Index feature selection algorithm. The proposed work was implemented and tested on AWID3 dataset. The experimental results show that the proposed model yields higher accuracy of 99.99% in detecting evil twin attacks.