Phising-Website_Detection

Introduction

In the last decades, the web and online services have revolutionized the modern world. However, by increasing our dependence on online services, as a result, online security threats are also increasing rapidly. One of the most common online security threats is a so-called Phishing attack, the purpose of which is to mimic a legitimate website such as online banking, e-commerce or social networking website in order to obtain sensitive data such as user-names, passwords, financial and health-related information from potential victims. The problem of detecting phishing websites has been addressed many times using various methodologies from conventional classifiers to more complex hybrid methods.

Data Features

1. having_IP_Address
2. URL_Length
3. Shortining_Service
4. having_At_Symbol
5. double_slash_redirecting
6. Prefix_Suffix
7. having_Sub_Domain
8. SSLfinal_State
9. Domain_registeration_length
10. Favicon
11. port
12. HTTPS_token
13. Request_URL
14. URL_of_Anchor
15. Links_in_tags
16. SFH
17. Submitting_to_email
18. Abnormal_URL
19. Redirect
20. on_mouseover
21. RightClick
22. popUpWidnow
23. Iframe
24. age_of_domain
25. DNSRecord
26. web_traffic
27. Page_Rank
28. Google_Index
29. Links_pointing_to_page
30. Statistical_report
31. Result

Data Scouce

UCI: https://archive.ics.uci.edu/ml/datasets/phishing+websites.

But I would reccomend using csv file available in this repository for ease of use. Download a copy of the repository and you will be good to go.

Project Overview

1. Exploratory Data Analysis

a. Studying the data in tabular form

b. Creating Basic plots and infering relations between data features visually

2. Data Pre-Processing

3. Train Test Split (80:20)

4. Machine Learning Classifiers

a. Logistic Regression

b. K-Nearest Neighbours

c. Decision Trees and Random Forest classifier

d. Support Vector Machine

5. Introduction to Basic Deep Learning Model and Neural Network

6. Comparing Prediction Accuracy