شماره ركورد كنفرانس :
5402
عنوان مقاله :
Intrusion Detection System Using GWO-Optimized Logistic Regression
عنوان به زبان ديگر :
Intrusion Detection System Using GWO-Optimized Logistic Regression
پديدآورندگان :
Fahad ALnaseri Zainab zainab.alnaseri@qu.edu.iq College of Computing and Information Technology University of Al-Qadisiyah, Iraq , Abdallah Al-Awsi Wasan Wasan.alawsi@qu.edu.iq College of Science, University of Al-Qadisiyah, Iraq , Khalilian Madjid khalilian@kiau.ac.ir Department of Computer Engineering, Karaj Branch, Islamic Azad University, Karaj, Iran
كليدواژه :
IoT , Gray Wolf Optimization , Logistic Regression , Intrusion Detection
عنوان كنفرانس :
اولين كنفرانس ملي پژوهش و نوآوري در هوش مصنوعي
چكيده فارسي :
The Internet of Things is able to grow and disseminate with the assistance of newly developed technologies. These devices have limited resources, which can be exploited in some way to generate distributed denial-of-service attacks that are widely distributed and extended until the server is completely reduced or stopped. Within the scope of this research, we suggest a framework for the detection of distributed denial-of-service attacks that ion fog computing. The proposed Gray Wolf Optimization Logistic Regression (GWO-LR) system is made up of an algorithm for logistic regression that is trained with the help of an algorithm for Gray Wolf Optimization GWO. The GWO-LR is used to solve the classification problem in the UNSW Bot-IoT 2018 database. The results showed that the classifier is able to detect attacks with a high accuracy of 98.88% and an F-measure of 99%.
