A Cybersecurity Procedure to Vulnerabilities Classification of Windows OS Based on Feature Selection and Machine Learning
Küçük Resim Yok
Tarih
2024
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer International Publishing Ag
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
The fast advancement of systems and technology has led to problems in several areas, with data protection and information security being particularly significant concerns. Cybersecurity is a recently developed field that comprises many strategies aimed at safeguarding sensitive data. By utilizing machine learning techniques, this study has improved the security of the Windows operating system. The categorization of Windows system vulnerabilities was performed using machine learning techniques such as Random Forest, Logistic Regression, Naive Bayes, K-Nearest Neighbors, and Support Vector Machine. The dataset was compiled using materials from the National Institute of Standards and Technology (NIST) and exploit-deb, Care was taken to ensure that the data is real and exists. The parameters that were assessed include accuracy, precision, recall, f1-score, and ROC AUC Score. The Random Forest approach yielded the most precise findings, with an accuracy rate of 97%. The findings indicated that the Random Forest methodology was successful in identifying vulnerabilities in security.
Açıklama
2nd International Conference on Forthcoming Networks and Sustainability in the AIoT Era (FoNeS-AIoT) -- JAN 27-29, 2024 -- Istanbul, TURKEY
Anahtar Kelimeler
Cybersecurity, Vulnerability, Feature Selection, Random Forest, Logistic Regression, Naive Bayes, K-Nearest Neighbors, SVM
Kaynak
Forthcoming Networks and Sustainability in the Aiot Era, Vol 1, Fones-Aiot 2024
WoS Q Değeri
N/A
Scopus Q Değeri
Q4
Cilt
1035
