IMPROVING THE EFFICIENCY OF BRUTE-FORCE ATTACK DETECTION USING DECISION TREES AN ANALYSIS STUDY

Nebras Jalel, Ibrahim (2023) IMPROVING THE EFFICIENCY OF BRUTE-FORCE ATTACK DETECTION USING DECISION TREES AN ANALYSIS STUDY. Journal of Engineering, Mechanics and Modern Architecture, 2 (11). pp. 17-25. ISSN 2181-4384

Text IMPROVING THE EFFICIENCY OF BRUTE-FORCE ATTACK DETECTION USING DECISION TREES AN ANALYSIS STUDY.pdf Download (350kB)

Abstract

Brute-force attacks are a common type of cyber attack in which an attacker repeatedly tries to guess a user's password or other login credentials. These attacks can be very time-consuming, but they can also be very successful, especially if the attacker is able to guess the credentials correctly. One way to improve the efficiency of brute-force attack detection is to use decision trees. Decision trees are a type of machine learning algorithm that can be used to classify data. In the context of brute-force attack detection, decision trees can be used to identify patterns in login attempts that are indicative of a brute-force attack. This paper presents an analysis of the use of decision trees for improving the efficiency of brute-force attack detection. The paper first reviews the literature on brute-force attacks and decision trees. Then, the paper presents the results of an experimental study that compares the performance of a decision tree-based brute-force attack detection system to a traditional rule-based system. The results of the experimental study show that the decision tree-based system is more efficient than the rule-based system. The decision tree-based system was able to detect brute-force attacks with a higher accuracy and a lower false positive rate. The findings of this paper suggest that decision trees can be an effective tool for improving the efficiency of brute-force attack detection. Decision trees are easy to implement and can be used to detect a wide range of brute-force attack patterns.

Item Type:	Article
Subjects:	T Technology > TJ Mechanical engineering and machinery
Divisions:	Postgraduate > Master's of Islamic Education
Depositing User:	Journal Editor
Date Deposited:	23 Nov 2023 07:49
Last Modified:	23 Nov 2023 07:49
URI:	http://eprints.umsida.ac.id/id/eprint/12640

Actions (login required)

View Item