Document Type : Research Paper
Authors
1
PhD. Student, Dept. of Information Technology Management, Islamic Azad University, Hamedan Branch, Hamedan, Iran
2
Assoc. Prof., Dept. of Computer Engineering, Islamic Azad University, Hamedan Branch, Hamedan, Iran
3
Assist. Prof., Dept. of Management, Islamic Azad University, Hamedan Branch, Hamedan, Iran
4
Assist. Prof., Dept. of Management, Islamic Azad University, Central Tehran Branch, Tehran, Iran
Abstract
One of the most important security challenges in e-banking security centers is the inability of the internet to deal with attacks. These attacks are easily implemented and can be controlled locally or remotely. Most of these attacks are successful in reaching the main targets of the attack and bring the attacker to their desires. The reason for this is that there are many mechanisms for launching attacks based on the characteristics of the victim's server, which makes it impossible to provide a comprehensive defense solution against the attacks. Several strategies have been proposed to identify and deal with these attacks. In this paper, a combination of algorithm for selecting genetic features and machine learning methods, including decision tree algorithm, deep neural network and KNN, are presented. Provide guidelines for validation, the results obtained with other techniques such as machine learning techniques and combined with other optimization methods are compared and evaluated. In this research, 10% of KDD Cup 99 dataset for simulation has been used. First, in the preprocessing of data, the values of all attributes are converted to numbers, and the output characteristic values are changed to two values of zero and one. The results of the research indicate that the accuracy of the proposed strategy for detecting intruders compared to other recent methods is about 5%.
Main Subjects
)