Comprehensive Method of Botnet Detection Using Machine Learning

Comprehensive Method of Botnet Detection Using Machine Learning

Kapil Kumar
Copyright: © 2021 |Pages: 25
DOI: 10.4018/IJOSSP.287613
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The botnet interrupts network devices and keeps control of the connections with the command, which controls the programmer, and the programmer controls the malicious code injected in the machine for obtaining information about the machines. The attacker uses a botnet to commence dangerous attacks as DDoS, phishing, despoil of information, and spamming. The botnet establishes with a large network and several hosts belong to it. In the paper, the author proposed the framework of botnet detection by using an artificial neural network. The author research upgrades the extant system by comprising cache memory to speed the process. Finally, for detection, the author used an analytical approach, which is known as an artificial neural network, that contains three layers—the input layer, hidden layer, output layer—and all layers are connected to correlate and approximate the results. The experiment result determines that the classifier with 25 epochs gives optimal accuracy is 99.78% and shows the detection rate is 99.7%.
Article Preview
Top

1. Introduction

Information security is becoming a significant aspect for each network to secure the devices and information from threats. The botnet is discovered to be the supreme perilous risk with an extreme loss of information to the private and imperative resources. It is found that botnets is an active plugin that attempts to enter into the computer by breaching privacy. Botnets endeavors to contravene the policy of security by violating pillars of security as the CIA needed to hold the security. The information system, which is controlled by the master remotely, is known as a botnet. The botnet is a kind of network, which is used to activate attacks as DDoS, phishing, sniffing, and blocking. The botnet passes the threat to the network. (Hodo, E., et al., 2016) found that botnet is a collection of zombies and zombies are a kind of program that is to used to insert the malicious code into the devices to get control. The attacker performs the activity by using the three-tier control architecture in which the programmer controls zombies and the master controls the programmer. The size of zombies could be very large that is used to form a big network and millions of infected hosts may belong to it. The bots can be used to create DDoS to immense-scale spamming, fraud, and identity theft.

The approaches of botnets (Venkatesan, S., et al., 2016) described as information accumulation in which zombies develop a network is known as the botnets. The botnets gather the processing information by obtaining the identity, password, and relationship data using the association rules, The next is the absence of authentic information that includes denial of service attacks, distributed denial of service attacks and spamming messages, sending of information from the forged source, and continuously sending the bogus request to the target machine to make the absence of the availability of legal services, and information manipulation that includes stealing the authentic information of authorized users by cracking the password for gaining unauthorized access to accounts. The botnet life cycle (Haddadi, F, et al., 2015) can be explained as the infection phase in which the master used its programmer to inject the infected code into the machine by various methods. The programmer controls the injector and the master control the programmer, the hidden phase involves the cleaning phase of evidence that is prepared by the master to remove any kind of evidence by which an actual source can be found. The other is the command and control phase in which the bot tries to connect to its server and after connecting, it will be a new bot in that network. In this phase, the bot gets the command of the programmer and the programmer get the command of the master, and the master controls the bots indirectly. The next is the attack phase in which the bot-master acts by controlling the bots. The last or final is the remove and release phase in which, the master tries to remove the bots from the surface without leaving any proof of the actual source.

The availability of the supply of service is important for reducing the time in general problem solving for the people. The everlasting addition of the usage of the internet emerged dangerous issues of cyber-attacks on a vulnerable application by accessing the assets in an unauthorized way. The networks are interconnected with each other by using web services, where security has been suffering to secure and safe information by passing through the IoT network. Hence, there is a need of developing a robust detection system that can detect any service which is the availing system of the legitimate user on behalf of legitimate service. Therefore, there is a need to develop a botnet detection system (BDS) for the security of IoT networks and play a significant role in the security of the devices from the botnets. (Vinaya Kumar et al., 2019) analyzed that many detection systems exist in the market. However, many of these systems have been suffering from the vulnerability that needs to be upgraded by research in this context.

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 14: 1 Issue (2023)
Volume 13: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 1 Issue (2015)
Volume 5: 3 Issues (2014)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing