Analysis of Feature Selection Approaches in Large Scale Cyber Intelligence Data with Deep Learning
Yükleniyor...
Tarih
2020
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
IEEE
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Ağ sistemlerinin her geçen gün katlanarak büyüyen
boyutu, saldırı yoğunluğunun ve türlerinin de artmasına neden
olmaktadır. Ağ içerisinde bu saldırıların tespiti, ağ güvenliğinin
başlıca problemlerindendir. Saldırı tespit sistemleri, bu problemle
başa çıkmak için geliştirilen bir yaklaşımdır. Saldırı tespit sistemlerinde işlenen büyük boyutlu veriler beraberinde karmaşıklığ
da getirmektedir. Bu çalışma, veri kümelerindeki karmaşıklığı gidermek için 6 farklı öznitelik seçme algoritmasının incelenmesini
ve bu algoritmaların sınıflandırma modellerindeki performanslarının karşılaştırılmasını içermektedir. Bu performanslar, açık
erişimli olarak sunulan CICIDS2017 veri seti üzerinde uygulanan
Derin Öğrenme modelleri ile analiz edilmiştir. Bu işlem sırasında
algoritmaların test sonuçları hem kendi aralarında hem de veri
setinin orijinal haliyle karşılaştırılmıştır. Uygulama sırasında veri
kümesindeki öznitelik sayıları çoklu sınıflandırma için 78’den
25’e, ikili sınıflandırma için 8’e düşürülmüştür. Elde edilen başarı
oranları bütün uygulamalarda %92’nin üzerindedir.
The size of the network systems that grows day by day causes the attack density and types to increase. Detection of these attacks within the network is one of the main problems of network security. Intrusion detection systems are an approach developed to deal with this problem. Large data processed in intrusion detection systems also brings complexity. This study includes examining 6 different attribute selection algorithms and comparing the performance of these algorithms in classification models to eliminate the complexity in data sets. These performances were analyzed with Deep Learning models applied on the open access CICIDS2017 data set. During this process, the test results of the algorithms were compared both among themselves and with the original form of the data set. During implementation, the number of attributes in the dataset was reduced from 78 to 25 for multiple classification and to 8 for binary classification. The success rates obtained are over 92% in all applications
The size of the network systems that grows day by day causes the attack density and types to increase. Detection of these attacks within the network is one of the main problems of network security. Intrusion detection systems are an approach developed to deal with this problem. Large data processed in intrusion detection systems also brings complexity. This study includes examining 6 different attribute selection algorithms and comparing the performance of these algorithms in classification models to eliminate the complexity in data sets. These performances were analyzed with Deep Learning models applied on the open access CICIDS2017 data set. During this process, the test results of the algorithms were compared both among themselves and with the original form of the data set. During implementation, the number of attributes in the dataset was reduced from 78 to 25 for multiple classification and to 8 for binary classification. The success rates obtained are over 92% in all applications
Açıklama
Anahtar Kelimeler
CICIDS2017; Cyber security; deep learning; feature selection; intrusion detection system, Siber güvenlik, saldırı tespit sistemi, derin öğrenme, öznitelik seçimi, CICIDS2017
Kaynak
2020 28th Signal Processing and Communications Applications Conference (SIU)
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
Cilt
Sayı
Künye
Ahmetoglu H.,Das R. (2020). Analysis of Feature Selection Approaches in Large Scale Cyber Intelligence Data with Deep Learning. 2020 28th Signal Processing and Communications Applications Conference (SIU). DOI. 10.1109/SIU49456.2020.9302200
Bağlantı
https://www.webofscience.com/wos/woscc/full-record/WOS:000653136100174?AlertId=d383397b-4355-449e-9419-70f9e0e77c15&SID=E5vn6BrBu1Ue95ENxH3
https://www.scopus.com/record/display.uri?eid=2-s2.0-85100301819&origin=resultslist&sort=plf-f&src=s&sid=c50b509052fefc89033228127c4b4cf2&sot=b&sdt=b&sl=34&s=DOI%2810.1109%2fSIU49456.2020.9302200%29&relpos=0&citeCnt=0&searchTerm=
https://hdl.handle.net/20.500.12514/2724
https://www.scopus.com/record/display.uri?eid=2-s2.0-85100301819&origin=resultslist&sort=plf-f&src=s&sid=c50b509052fefc89033228127c4b4cf2&sot=b&sdt=b&sl=34&s=DOI%2810.1109%2fSIU49456.2020.9302200%29&relpos=0&citeCnt=0&searchTerm=
https://hdl.handle.net/20.500.12514/2724
