Detection of phishing websites using ML

1. Detecting Phishing Websites Using Machine Learning
UNDER ESTEEMED GUIDANCE OF:
MS. LAVANYA
ASST.PROFESSOR
TEAM MEMBERS:
19H51A1258 - D.B.SRAVYA
20H55A1201 - B.SAIRAM
20H55A1202 - P.SAI
DEPARTMENT OF INFORMATION TECHNOLOGY

2. LIST OF CONTENTS
 ABSTRACT
 INTRODUCTION
 RESEARCH OBJECTIVE
 PROJECT SCOPE
 CONCLUSION
 REFERENCES

3. ABSTRACT
 Phishing website is one of the internet security problems, described as the process of attracting online
users to obtain their sensitive information such as usernames and passwords.
 In this project, we offer an intelligent system for detecting phishing websites.
 The system acts as an additional functionality to an internet browser as an extension that automatically
notifies the user when it detects a phishing website.
 The system is based on a machine learning method, particularly supervised learning,we have selected the
Random Forest technique due to its good performance in classification.
 Our focus is to pursue a higher performance classifier by studying the features of phishing website and
choose the better combination of them to train the classifier.

4. INTRODUCTION
 In today’s world, internet has become an integral part of the twenty-first century It has become a
valuable mechanism for supporting public transactions such as e-banking and e-commerce.
 That has led the users to trust it is convenient to provide their private information to the Internet. As a
result, the security thieves that have started to target this information have become a major security
problem. Phishing websites are considered to be one of these problems.
 They are using a social engineering trick, which can be described as fraudsters that try to manipulate the
user into giving them their personal information based on exploiting human vulnerabilities rather than
software vulnerabilities.

5. Classification of fishing attack techniques
Technical subterfuge: In these attacks, attacker intends
to gain the access through a tool / technique. On the one
hand, users believe the network and on the other hand,
the network is compromised by the attackers.
Social engineering:. In these attacks, attackers focus
on the group of people or an organization and trick
them to use the phishing URL.

6. RESEARCH OBJECTIVE
 Nowadays Phishing becomes a main area of concern for security researchers because it is not
difficult to create the fake website which looks so close to legitimate website.
 The main objective is to prevent these activities, we are going to develop our project using a
website as a platform for all the users.
 This is an interactive and responsive website that will be used to detect whether a website is
legitimate or phishing.
 This website is made using different web designing languages which include HTML, CSS, Javascript
and Django.

7. PROJECT SCOPE
 Reduce dependency, cost & license on third-party external software
 Better insights into online behavior of employs real-time protection for employee who access malicious
websites or click on phishing links.
 Email filtering solutions help in filtering phishing/spam emails, but this provides holistic protection for all
outgoing internet traffic.
 The website is created with an opinion such that people are not only able to distinguish between legitimate
and fraudulent website, but also become aware of the mal-practices occurring in current world.
 They can stay away from the people trying to exploit one’s personal information, like email address, password,
debit card numbers, credit card details, CVV, bank account numbers, and the list goes on.

8. CONCLUSION
 We are developing this System for completely detecting the fishing websites in the internet and
provide safe browsing for the user.
 The ML based phishing techniques depend on website functionalities to gather information that
can help classify websites for detecting phishing sites.
 The problem of phishing cannot be eradicated, nonetheless can be reduced by combating it in two
ways,
I. improving targeted anti-phishing procedures and techniques
II. informing the public on how fraudulent phishing websites can be detected and identified.
 In addition, this project can be extended in order to generate an outcome for a larger network and
protect the privacy of an individual.

9. REFERENCES
1. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8504731/#:~:text=The%20phishing%20detection%
20method%20focused,with%20SVM%20Classification%20are%20detected.
2. Y. Zhang, J. I. Hong, and L. F. Cranor, ”Cantina: A Content-based Approach to Detecting Phishing
Web Sites,” New York, NY, USA, 2007, pp. 639-648.
3. M. Blasi, ”Techniques for detecting zero day phishing websites.” M.A. thesis, Iowa State University,
USA, 2009
4. L. Breiman, ”Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5-32, Oct. 2001.
5. [22] J. VanderPlas, Python data science handbook, 1st ed. 1005 Gravenstein Highway North,
Sebastopol, CA 95472.: OReilly Media, Inc., 2016, pp. 331–515