DETECTION OF PHISHING WEBSITES USING

MACHINE LEARNING
BY

ADEDIRAN ADENIYI GOODNESS

(SSE/017/18295)

SUPERVISED BY DR. A.O. AKINWUNMI

 PRESENTATION OUTLINE

01 02 03

INTRODUCTION STATEMENT OF AIM AND

PROBLEM OBJECTIVES
 PRESENTATION OUTLINE

04 05 06
SCOPE
OF SIGNIFICANC METHODOLOGY
STUDY E OF STUDY
 PRESENTATION OUTLINE

07 08 09
LITERATURE EXISTING AND BENEFIT OF
REVIEW PROPOSED PROPOSED
SYSTEM SYSTEM
 PRESENTATION OUTLINE
REFERENCE

10 11 12
SYSTEM DESIGN IMPLEMENTATION
& CONCLUSION
(Diagram)
CONTRIBUTION TO
KNOWLEDGE
 INTRODUCTION
The Internet global connectivity is regarded as a
crossroads where users can meet and share
information. This is the primary reason phishers
choose this method of data exchange as a point
of contact to conduct widespread phishing
attacks by infecting computers with spyware that
directs people to bogus websites.

Phishing attack is one of the most dangerous

threats to online accounts and data because these
attacks pose as a trustworthy firm or person, and
they employ social engineering techniques to
(Source: Designed by Freepik, n.d.)
make victims more likely to fall for the scam.
 STATEMENT OF PROBLEM
Phishing attacks have gotten increasingly complex,
it is very difficult for an average person to
determine if an email message link or website is
legitimate. Cyber-attacks by criminals that employ
phishing schemes are so prevalent and successful
nowadays.

Hence, this project seeks to address fake URLs and

domain names by identifying phishing website
links. Therefore, having a web application that
provides the user an interface to check if a URL is (Source: Designed by Freepik, n.d.)
Phishing or legitimate will help decrease security
risks to individuals and organizations.
 AIM
The aim of this project is to detect phishing websites using machine learning and
deep neural networks by developing a web application that allows users to check if
a URL is phishing or legitimate and have access to resources to help tackle
phishing attacks.
OBJECTIVES
i. dataset collection and pre-processing;

ii. machine learning model selection and development ;

iii. development of a web-based application for detection;

(Source: Designed by Freepik, n.d.)
iv. Integration of the developed model to web application
 SCOPE OF STUDY
This study explores machine
learning models that uses datasets
gotten from open-source platform
to analyze website links and
distinguish between phishing and
legitimate URL links.

The model will be integrated into

a web application, allowing a
user to predict if a URL link is
legitimate or phishing. This
online application is compatible
with a variety of browsers.
(Source: Designed by Freepik, n.d.)
 SIGNIFICANCE OF THE PROJECT
Due to the fraudulent websites built on the World Wide Web in the previous decade to mimic
reputable websites and steal financial assets from users and organizations. Hence phishing
attack has become so prevalent such that it has cost the internet community and other
stakeholders hundreds of millions of dollars. Thus, robust countermeasures that can identify
phishing are required.

These are the challenges to be addressed in this project:

I. Reduce the rate of financial theft from individuals and organizations online.
II. Educate Internet Users on the deception technique of phishers.
III. Educate Internet users on the countermeasures of phishing attack.
Image of Cyber attack Counter-measure (Source: Designed by Freepik, n.d.)
 METHODOLOGY
An extensive review was done on existing works of literature and machine learning
models on detecting phishing websites to best decide the classification models to
solve the problem of detecting phishing websites.

Data Collection
 METHODOLOGY

Architectural design of proposed system zx

LITERATURE REVIEW
 ANALYSIS OF EXISTING SYSTEM
The existing system of phishing detection techniques suffer low detection
accuracy and high false alarm especially when different phishing approaches are
introduced. Above and beyond, the most common technique used is the blacklist-
based method which is inefficient in responding to emanating phishing attacks
since registering new domain has become easier, no comprehensive blacklist can
ensure a perfect up-to-date database for phishing detection.
 ANALYSIS OF PROPOSED SYSTEM
The proposed phishing detection system utilizes different machine learning models and
deep neural networks. The system comprises of two major parts, which are the machine
learning models and a web application. These models consist of Decision Tree, Support
Vector Machine, XGBooster, Multilayer Perceptions, Auto Encoder Neural Network and
Random Forest.

These models are selected after different comparison based performance of multiple
machine learning algorithms. Each of these models is trained and tested on a website
content-based feature, extracted from both phishing and legitimate dataset.

Hence, the model with the highest accuracy is selected and integrated to a web application
that will enable a user to predict if a URL link is phishing or legitimate
 BENEFIT OF PROPOSED SYSTEM
I. Will be able to differentiate between phishing(0) and legitimate(1) URLs

II. Will help reduce phishing data breach for organization

III. Will be helpful to individuals and organizations

IV. Will be easy to use

(Source: Credibly, n.d.)

Machine
Learning
process
Flowchart of
Web
Application
Use case of
web
Application
Implementation
 Data Collection

Dataset of Phishing URLs Dataset of Legitimate URLs

INTEGRATION OF MODEL TO
WEB APPLICATION
 CONTRIBUTION TO KNOWLEDGE
This project provides an efficient and effective way for detecting phishing websites (URL)
by exploring Data science classification technique.
This project tend to improve the previous technique for detecting phishing websites by
employing different machine learning classification models and deep neural network to
distinguish between phishing and legitimate URL links.
Hence, This project provides a new and faster way to help users detect if a URL link is
phishing or legitimate and also provide them access to educational resources about phishing
attacks.
(Source: Designed by Freepik, n.d.)
 CONCLUSION
The contribution of this research work is to help both
individuals and organization identify and understand
phishing techniques used by phisher as well as help them
detect phishing URL attack effectively and efficiently by
employing machine learning models instead of the
previous method of detecting phishing website.
 Recommendation
Through this project, one can know a lot about phishing
attacks and how to prevent them. This project can be
taken further by creating a browser extension that can be
installed on any web browser to detect phishing URL
Links.
 REFERENCES
Cyber attacker hacking into email server by Freepik. (n.d.). Retrieved from https://
www.freepik.com/free-vector/cyber-attacker-hacking-into-email-server_5259895.htm#page=1&q
uery=cyber%20phishing&position=2
People connecting jigsaw pieces of a head together by Freepik. (n.d.). Retrieved from https://
www.freepik.com/free-vector/people-connecting-jigsaw-pieces-head-together_3425145.htm#pa
ge=1&query=knowledge&position=4
Group of people holding question mark icons by Freepik. (n.d.). Retrieved from https://
www.freepik.com/free-vector/group-people-holding-question-mark-icons_3530048.htm#page=1
&query=PROBLEM&position=12
Golden cup with arrow hitting in the target center by Freepik. (n.d.). Retrieved from
https://www.freepik.com/free-vector/golden-cup-with-arrow-hitting-target-center_1311358.htm#p
age=1&query=AIM&position=25
Affective computing abstract concept illustration by Freepik. (n.d.).Retrieved from
https://www.freepik.com/free-vector/affective-computing-abstract-concept-
illustration_11668804.htm#page=1&query=machine%20learning&position=17
THANKS FOR
LISTENING