A Machine-Learning Approach to Phishing Detection and Defense

Cover
Title Page
Copyright Page
Contents
Abstract
List of Tables
List of figures
List of abbreviation
Chapter 1 - Introduction
	1.1 -  Introduction
	1.2 -  Problem background
	1.3 -  Problem statement
	1.4 -  Purpose of study
	1.5 -  Project objectives
	1.6 -  Scope of study
	1.7 -  The significance of study
	1.8 -  Organization of report
Chapter 2 - Literature Review
	2.1 -  Introduction
	2.2 -  Phishing
	2.3 -  Existing anti-phishing approaches
	2.3.1 -  Non-Content-Based Approaches
	2.3.2 -  Content-Based Approaches
	2.3.3 -  Visual Similarity-Based Approach
	2.3.4 -  Character-Based Approach
	2.4 -  Existing techniques
	2.4.1 -  Attribute-Based Anti-Phishing Technique
	2.4.2 -  Generic Algorithm-Based Anti-Phishing Technique
	2.4.3 -  An Identity-Based Anti-Phishing Techniques
	2.5 -  Design of classifiers
	2.5.1 -  Hybrid System
	2.5.2 -  Lookup System
	2.5.3 -  Classifier System
	2.5.4 -  Ensemble System
			2.5.4.1 - Simple Majority Vote
	2.6 -  Normalization
	2.7 -  Related work
	2.8 -  Summary
	Chapter 3 - Research Methodology
	3.1 -  Introduction
	3.2 -  Research framework
	3.3 -  Research design
	3.3.1 -  Phase 1: Dataset Processing and Feature Extraction
	3.3.2 -  Phase 2: Evaluation of Individual Classifier
	3.3.2.1 -  Classification Background
	3.3.2.2 -  Classifier Performance
	3.3.2.2.1 -  C5.0 Algorithm
	3.3.2.2.2 -  K-Nearest Neighbour
	3.3.2.2.3 -  Support Vector Machine (SVM)
	3.3.2.2.4 -  Linear Regression
	3.3.3 -  Phase 3a: Evaluation of Classifier Ensemble
	3.3.4 -  Phase 3b: Comparison of Individual versus Ensemble Technique
	3.4 -  Dataset
	3.4.1 -  Phishtank
	3.5 -  Summary
	Chapter 4 - Feature Extraction
	4.1 -  Introduction
	4.2 -  Dataset processing
	4.2.1 -  Feature Extraction
	4.2.2 -  Extracted Features
	4.2.3 -  Data Verification
	4.2.4 -  Data Normalization
	4.3 -  Dataset division
	4.4 -  Summary
	Chapter 5 - Implementation and Result
	5.1 -  Introduction
	5.2 -  An overview of the investigation
	5.2.1 -  Experimental Setup
	5.3 -  Training and testing model (baseline model)
	5.4 -  Ensemble design and voting scheme
	5.5 -  Comparative study
	5.6 -  Summary
	Chapter 6 - Conclusions
	6.1 -  Concluding remarks
	6.2 -  Research contribution
	6.2.1 -  Dataset Preprocessing Technique
	6.2.2 -  Validation Technique
	6.2.3 -  Design Ensemble Method
	6.3 -  Research implication
	6.4 -  Recommendations for future research
	6.5 -  Closing note
	References