This document summarizes a project that aims to detect phishing websites and encrypt user search data for privacy. The objectives are to detect malicious URLs and encrypt user search data before storing it on the server. The proposed system uses a support vector machine to classify URLs as safe or unsafe. It also uses RSA encryption to encrypt user search URLs before transmitting them to the server. The system requirements, module descriptions, algorithms and screenshots are also outlined in the document.

1. PHISHING WEBSITE DETECTION
GUIDE NAME :C.SAKUNTHALA M.E..,
SUBMITTED BY
ABINAYA S 812819205002
ARUL VINCENT RAJ A 812819205008
SAHANA BANU B 812819205023

2. OBJECTIVE
• Objective of the proposed project is to detects Malicious or Fake URLs to prevent
the users accessing from Unsafe URLs.
• Also provide secure encryption method to encrypt the user search data before
stored on the server.

3. INTRODUCTION
• Phishing imitates the characteristics and features of emails and makes it look the same as
the original one. It appears similar to that of the legitimate source.
• The user thinks that this email has come from a genuine company or an organisation.
This makes the user to forcefully visit the phishing website through the links given in the
phishing email.
• These phishing websites are made to mock the appearance of an original organisation
website.
• The phishers force user to fill up the personal information by giving alarming messages
or validate account messages etc..

4. ABSTRACT
• The user’s browsing data are used to extract valuable information about users interest. These data
are under the risk of being exposed to third parties. Proposed a model which encrypts the user’s
search data. Prevents privacy of data from both outside analysts and the intermediate server. It also
supports unsafe URL detection, to prevent users from accessing malicious URL. AES algorithm is
used for encrypting and decrypting user’s browsing data.

5. EXISTING SYSTEM
• PhishSim as a tool to effectively detect slightly modified or near-similar phishing websites using
prototype-based learning algorithms.
• The Normalized Compression Distance, which is a parameter-free and application independent
distance metric to measure similarities between websites’ HTML content.
• This tool works by measuring the pairwise similarity between websites in the dataset, clustering
these websites.
• Performing phishing classifications based on whether a website is grouped in the same cluster with
a known phishing website.

6. ISSUES IN THE EXISTING SYSTEM
• Creating metadata of URLs fails when the server receives multiple prefixes for a URL.
• Only capable of detecting trained URL.
• Multiple prefix matching can reduce the uncertainty of URL re-identification.
• Does not support for large dataset classification for accurate detection of phishing
website.

7. PROPOSED SYSTEM
• The major detection process is checking the URL to be visited by a user with the records in an encrypted
blacklist.
• The major detection process is checking the URL to be visited by a user with the records in an encrypted
blacklist.
• Support Vector Machine: Used for Classifying safe and unsafe URLs.
• Once a match is found (i.e., the URL is unsafe), the corresponding web page will not be loaded and also
provide safe URL details based on user’s search history.
• Also provide keyword based malicious detection using predefined keyword set.
• Users’ search URL data are encrypted first using RSA algorithm and then stored in intermediate server.

8. ADVANTAGES
• Provide the security to user searching data .
• Encrypt user viewed history .
• Allow only trained normal website .
• Block the url in the block storage

9. SYSTEM REQUIREMENTS
• Hardware Requirements
• Processor - Dual core processor 2.6.0 GHZ
• RAM - 1GB
• Hard disk - 160 GB
• Compact Disk - 650 Mb
• Keyboard - Standard keyboard
• Monitor - 15 inch color monitor

10. SYSTEM REQUIREMENTS
• Software Requirements
• Operating system - Windows OS
• Front End - ASP.NET
• Back End - SQL SERVER
• Application - Web Application
• Tool - Visual Studio 2010

11. BLOCK DIAGRAM

12. MODULE DECOMPOSITION
• Framework Construction
• User Registration and Login
• URL Search
• Unsafe URL Detection
• Search URL Encryption
• Access Search History
• Feedback System

13. MODULE DESCRIPTION
• Framework Construction
• Admin can set the framework to support efficient URL matching and unsafe URL
detection process.
• In this application, the URL data are converted into encrypted format.
• Black list should contain the unsafe URL’s with keywords.
• This will help to prevent from user search data leakage and malicious website access
on server.

14. MODULE DESCRIPTION
• User Registration and Login
• The user enrollment manages the user registration and login process with the help of
web server.
• Registration process collects the user details and stored on the data base.
• The login phase verifies the username and password.
• If the value match into the server data base then login to the account.
• Otherwise can’t access the user account.
• The server totally monitoring the user activity.

15. MODULE DESCRIPTION
• URL Search
• User can search data using URL or Specified Keyword.
• The verification of URLs and keywords is very essential in order to ensure that user
should be prevented from visiting malicious websites.
• SVM mechanisms have been proposed to detect the malicious URLs.
• One of the basic features that a mechanism should posses is to allow the fake URLs
that are requested by the client and prevent the malicious URLs before reaching the
user.
• This is achieved by notifying the user that it was a malicious website.

16. MODULE DESCRIPTION
• Unsafe URL Detection
• This proposed framework uses SVM classification models to detect a malicious URL
and categorize the malicious URL as one of a phishing URL.
• The techniques extract features associated with the known URLs, and use the
machine learning algorithms to train the unknown malicious URL.
• Here, the new URL will be matched and tested with every previously known
malicious URL in the black list.
• This also allows users to provide suggestions to add malicious URLs.

17. MODULE DESCRIPTION
• Search URL Encryption
• User could search the data through this website.
• The URL of searched data transmitted to server in secure manner.
• URL has converted into encrypted format using Homomorphic RSA encryption
process.
• Then the encrypted details are shared to server for identification.

18. MODULE DESCRIPTION
• Access Search History
• This module explains about search data retrieval.
• Users are allowed to view their search history in secure manner.
• Users first need to authenticate using their username and password.
• Then they get OTP in SMS format, that will helps to decrypting the URL
data.

19. MODULE DESCRIPTION
• Feedback System
• Feedback system helps to overcome the problems faced by user during web search
process.
• User can send their feedback regarding, search efficiency.
• Also they will be allowed to provide suggestion for adding further URLs in blacklist.
• Admin can view URL suggestion provided by user, and add the malicious URLs in
blacklist.
• This helps to enhance the performance of blacklist storage in phishing detection.

20. ALGORITHM
• RSA Algorithm
• RSA algorithm is an asymmetric cryptography algorithm.
• Asymmetric actually means that it works on two different keys i.e. Public
Key and Private Key.
• As the name describes that the Public Key is given to everyone and the Private key is
kept private.

21. ALGORITHM
• Homomorphic RSA Encryption
• Key Generation Process
• Step 1: Generate two large random primes, p and q, of approximately equal size such that their product n=pq is of the
required bit length, e.g. 1024 bits.
• Step 2: Compute n=pq and ϕ=(p−1)(q−1).
• Step 3: Choose an integer e, 1<e<ϕ, such that gcd (e,ϕ) = 1.
• Step 4: Compute the secret exponent d, 1<d<ϕ, such that ed≡1modϕ.
• The public key is (n,e) and the private key (d,p,q). Keep all the values d, p, q and ϕ secret.
• n is known as the modulus.
• e is known as the public exponent or encryption exponent or just the exponent.
• d is known as the secret exponent or decryption exponent.

22. ALGORITHM
• Encryption
• Step 1: Obtains the recipient B's public key (n,e).
• Step 2: Represents the plaintext message as a positive integer mm with 1<m<n.
• Step 3: Computes the ciphertext c =
• Step 4: Sends the ciphertext cc to B.
• Decryption
• Recipient B does the following:-
• Step1: Uses his private key (n,d) to compute m=
• Step 2: Extracts the plaintext from the message representative mm.

23. ALGORITHM
• Support Vector Machine (SVM)
• Support Vector Machine (SVM) is a supervised algorithm based on machine learning
• In this work, plot each data item as a point in n-dimensional space with the value of every feature
being the count of a particular coordinate.
• Then, we perform classification by finding the hyper-plane that differentiates the two classes very
well.
• Support Vectors are simply the co-ordinates of individual observation.
• Support Vector Machine is best for segregates the two classes (hyper-plane/ line).
• The hyperplane is the line with the biggest margin to both groups.

24. CONCLUSION
• The proposed model ensures that the users’ search URL data is completely privacy
preserved.
• Using asymmetric key encryption concept like RSA algorithm and differential privacy
makes sure that no one can predict the users’ interest.
• It avoids the access of malicious websites.

25. SCREEN SHOT
Admin login page

26. SCREEN SHOT
Training page

27. SCREEN SHOT
New user login

28. SCREEN SHOT
url searching page

29. SCREEN SHOT
Alert page

30. SCREEN SHOT
View history

31. SCREEN SHOT
Feed back page

32. REFERENCES
• [1] Ahammad, SK Hasane, Sunil D. Kale, Gopal D. Upadhye, Sandeep Dwarkanath Pande, E. Venkatesh Babu, Amol V.
Dhumane, and Mr Dilip Kumar Jang Bahadur. "Phishing URL detection using machine learning methods." Advances in
Engineering Software 173 (2022): 103288
• [2] Butnaru, Andrei, AlexiosMylonas, And Nikolaos Pitropakis. "Towards Lightweight Url-Based Phishing
Detection." Future Internet 13, No. 6 (2021): 154
• [3] Butt, Muhammad Hassaan Farooq, Jian Ping Li, Tehreem Saboor, Muhammad Arslan, And Muhammad Adnan
Farooq Butt. "Intelligent Phishing Url Detection: A Solution Based On Deep Learning Framework." In 2021 18th
International Computer Conference On Wavelet Active Media Technology And Information Processing
(Iccwamtip), Pp. 434-439. Ieee, 2021.
• [4] Mourtaji, Youness, Mohammed Bouhorma, Daniyal Alghazzawi, Ghadah Aldabbagh, And Abdullah Alghamdi.
"Hybrid Rule-Based Solution for Phishing Url Detection Using Convolutional Neural Network." Wireless
Communications And Mobile Computing 2021 (2021): 1-24.
• [5] Odeh, Ammar, Ismail Keshta, And Eman Abdelfattah. "Machine Learning techniques for Detection Of Website
Phishing: A Review For Promises And Challenges." In 2021 Ieee 11th Annual Computing And Communication
Workshop And Conference (Ccwc), Pp. 0813-0818. Ieee, 2021.