Classification and Detection of email Phishing using random Forest supervised-unsupervised machine learning algorithms

Shah, Akshat (2021) Classification and Detection of email Phishing using random Forest supervised-unsupervised machine learning algorithms. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (663kB) | Preview
Preview	PDF (Configuration manual) Download (722kB) | Preview

Abstract

In the cutting edge time, all administrations are kept up with on the web and everybody go through it, to pace their everyday actions. This incorporate social as well as monetary actions which includes utilization of classified data to complete the expected assignment. With the increment in use of such functions set forth the significance of getting the information used to operate such activities. In the course of the decades phishing has gotten a genuine danger to the general public by taking classified data to get hold of these resources. As with the specific aim on how well they operate, we study current and prospective email phishing technique. In this the main focus or we can say the prime suspect is securing email phishing, we will discuss the perception of phishing email and the task to detect email as a part of online active room. This paper researches and reports the utilization of irregular woods AI calculation in order of phishing assaults, with the significant target of fostering an improved phishing email classifier with better expectation exactness and less quantities of components. In spite of ongoing progressions in examination techniques, there stay many concerns with respect to the plausibility and authenticity of email phishing testing techniques. For this research, we use Naive Bayes, support vector machine, Random forest classifier, Logistic regression, as the classification method and recognise the conclusion by using recall, accuracy, training time, f1 ratings and correctness as the enhancement of the presentation performed and justify emails as legitimate or not through supervised and unsupervised approaches.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security H Social Sciences > HV Social pathology. Social and public welfare > Criminology > Crimes and Offences > Cyber Crime
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Clara Chan
Date Deposited:	01 Nov 2021 17:18
Last Modified:	01 Nov 2021 17:18
URI:	https://norma.ncirl.ie/id/eprint/5126

Actions (login required)

View Item