How to detect phishing website using three model ensemble classification

Other Title(s)

كيفية اكتشاف موقع التصيد الاحتيالي باستخدام تصنيف المجموعة ثلاثية النماذج

Dissertant

al-Sharif, Yusra Majid

Thesis advisor

Abu Saimah, Hisham

University

Middle East University

Faculty

Faculty of Information Technology

Department

Computer Science Department

University Country

Jordan

Degree

Master

Degree Date

2020

English Abstract

As the number of web users increases, phishing attacks are gradually increasing.

In order to effectively respond to various phishing attacks, a proper understanding of phishing attacks is necessary, and appropriate response methods must be utilized.

To this end, in this thesis, three ensemble classification to detect the phishing website attack is analyzed.

Through this analysis, it is possible to reconsider the awareness of phishing attacks and prevent the damage of phishing attacks in advance.

In addition, a countermeasure is proposed for each phishing type based on the analyzed content.

The proposed countermeasure is a method that utilizes appropriate website features for each step.

To determine the effectiveness of the countermeasure, every classification model is generated through the proposed feature extraction method and the accuracy of each model is verified.

In conclusion, the proposed method in this thesis is the basis for strengthening anti-phishing technology and the basis for strengthening website security.

Therefore, ensemble methods are meta-algorithms that combine several machine learning techniques into one predictive model in order to decrease variance bagging or improve prediction stacking.

Phishing website detection algorithm using three ensemble classification, which is proposed in this thesis can get the high phishing website detecting accuracy, because three classification algorithms Random Forest, Support Vector Machine, and Decision Tree are combined in one system.

All the achieved proposed algorithm results have shown the highest accuracy of 98.52% than others.

It is higher 1.26% than Random Forest, 3.16% than Support Vector Machine, and 2.65% than the Decision Tree algorithm.

Main Topic

Information Technology and Computer Science

Topics

No. of Pages

68

Table of Contents

Table of contents.

Abstract.

Abstract in Arabic.

Chapter One : Introduction.

Chapter Two : Background and literature review.

Chapter Three : Methodology and the proposed model.

Chapter Four : Implementation and evaluation results.

Chapter Five : Conclusion and future work.

References.

American Psychological Association (APA)

al-Sharif, Yusra Majid. (2020). How to detect phishing website using three model ensemble classification. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-970879

Modern Language Association (MLA)

al-Sharif, Yusra Majid. How to detect phishing website using three model ensemble classification. (Master's theses Theses and Dissertations Master). Middle East University. (2020).
https://search.emarefa.net/detail/BIM-970879

American Medical Association (AMA)

al-Sharif, Yusra Majid. (2020). How to detect phishing website using three model ensemble classification. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-970879

Language

English

Data Type

Arab Theses

Record ID

BIM-970879