A Predictive Technique using Random Forest Classifier for Phishing Malicious Attack

Authors

Abdullah Alhaj, Department of Information Technology, Faculty of Information Technology and Systems, The University of Jordan, Aqaba 77110, JordanFollow
Mua’ad Abu-Faraj, Department of Computer Information Systems, Faculty of Information Technology and Systems, The University of Jordan, Aqaba 77110, JordanFollow
Basel J. A. Ali, College of Economics and Management (CoEM), Al Qasimia University, Sharjah, United Arab EmiratesFollow

Author Country (or Countries)

Jordan

Abstract

A person with an email account is always vulnerable to fraud. An email account can be exploited by using a type of social engineering attack where the attackers trick the victims to steal user credentials by masquerading as a trusted entity. Email phishing has become the major action performed in various sectors such as banking, business, any enterprise or social media etc. While the action of phishing, the attackers make use of another technique called email spoofing. Email spoofing is not much different from email phishing since the email spoofing involves the usage of forged email header pretending as an entity created by a person of a trusted source. Phishing always has a malicious intent which means the person behaves knowingly or purposefully to cause them harm without a legal reasoning. Since the globe has more victims, we come across a large dataset. The major objective of the study is to determine the performance factors based on the phishing using random forest classifiers. For analysing a predictive model, we need a proper technique or an algorithm. In this case the random forest algorithm is accurate because it is built with many decision trees that produce a predictive model about the error rate.

Digital Object Identifier (DOI)

https://dx.doi.org/10.18576/amis/170622

Recommended Citation

Alhaj, Abdullah; Abu-Faraj, Mua’ad; and J. A. Ali, Basel (2023) "A Predictive Technique using Random Forest Classifier for Phishing Malicious Attack," Applied Mathematics & Information Sciences: Vol. 17: Iss. 6, Article 28.
DOI: https://dx.doi.org/10.18576/amis/170622
Available at: https://digitalcommons.aaru.edu.jo/amis/vol17/iss6/28