A comparative study between deep learning algorithm and bayesian network on Advanced Persistent Threat (APT) attack detection

Ooi, Hui Ni and Ab Rahman, Nurul Hidayah (2021) A comparative study between deep learning algorithm and bayesian network on Advanced Persistent Threat (APT) attack detection. Penerbit UTHM, UTHM.

Text
P13606_fc6b8cdc19cf367513bb5fecde8c41eb.pdf
Restricted to Registered users only
Download (1MB) | Request a copy

Official URL: https://doi.org/10.30880/aitcs.2021.02.02.015

Abstract

Advanced Persistent Threat (APT) attacks are a major concern for the cybersecurity in digital world due to their advanced nature. Attackers are skilful to cause maximal destruction for targeted cyber environment. These APT attacks are also well funded by governments in many cases. The APT attacker can achieve his hostile goals by obtaining information and gaining financial benefits regarding the infrastructure of a network. It is highly important to study proper countermeasures to detect these attacks as early as possible due to sophisticated methods. It is difficult to detect this type of attack since the network may crash because of high traffic. Hence, in this study, this research is to study the comparison between Multilayer Perceptron and Naïve-Bayes of APT attack detection. Since the APT attack is persistent and permanent presence in the victim system, so minimal false positive rate (FPR) and high accuracy detection is required to detect the APT attack detection. Besides, Multilayer Perceptron algorithm has high true positive rate (TPR) in the detection of APT attack compared to Naïve Bayes algorithm. This means that Multilayer Perceptron algorithm can detect APT attack more accurately. Based on the result, it also can conclude that the lower the false positive rate (FPR), the more accurate to detect APT attack. Lastly, the research would also help to spread the awareness about the APT intrusion where it possibly can cause huge damage to everyone.

Item Type:	Other
Uncontrolled Keywords:	Accuracy; APT attack; Bayesian Network; deep learning algorithm; NSL-KDD dataset
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Computer Science and Information Technology > Department of Software Engineering
Depositing User:	Mr. Abdul Rahim Mat Radzuan
Date Deposited:	14 Mar 2022 02:11
Last Modified:	14 Mar 2022 02:11
URI:	http://eprints.uthm.edu.my/id/eprint/6696

Actions (login required)

View Item