Feature Selection Approach for Phishing Detection
Küçük Resim Yok
Tarih
2022
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Institute of Electrical and Electronics Engineers Inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
This study offers a novel approach to the feature selection. We propose a method to reduce the number of features while maintaining high detection accuracy by combining two popular feature importance methods and the GRiS mean method. The proposed model also improves the training time, test time, and usage of memory. Among the Ill features of the latest published phishing website detection dataset, the efficient features were selected with this approach. Using the Random Forest algorithm and the proposed feature selection approach with only nineteen features, the accuracy of phishing detection can reach up to 97.12%. © 2022 IEEE.
Açıklama
3rd International Informatics and Software Engineering Conference, IISEC 2022 -- 15 December 2022 through 16 December 2022 -- Ankara -- 185735
Anahtar Kelimeler
feature selection, machine learning, phishing, random forest
Kaynak
3rd International Informatics and Software Engineering Conference, IISEC 2022
WoS Q Değeri
Scopus Q Değeri
N/A
