Scribd
Upload
116 views8 pages

Phishhaven: An Efficient Real-Time Al Phishing Urls Detection System

This document describes PhishHaven, a machine learning-based system for detecting phishing URLs in real-time. It employs lexical analysis and URL encoding as features to train 10 models to classify URLs. A GUI allows users to enter URLs and view prediction results. The system aims to prevent phishing attacks by identifying both human-made and AI-generated phishing URLs with high accuracy.

Uploaded by

dj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
116 views8 pages

Phishhaven: An Efficient Real-Time Al Phishing Urls Detection System

This document describes PhishHaven, a machine learning-based system for detecting phishing URLs in real-time. It employs lexical analysis and URL encoding as features to train 10 models to classify URLs. A GUI allows users to enter URLs and view prediction results. The system aims to prevent phishing attacks by identifying both human-made and AI-generated phishing URLs with high accuracy.

Uploaded by

dj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

PhishHaven

An Efficient Real-Time Al Phishing URLs Detection System

GUIDE NAME STUDENT NAME


Asst.prof.Deepthy J Mariya jose

School of computer science pg MCA Lateral 2019

Dist Roll no:29


ABSTRACT

• The project is focuses to detect and prevent the phishing URL attacks.
• It is a machine learning-based detection system called PhishHaven to identify AI-generated as well as
human-crafted phishing URLs.
• PhishHaven employs lexical analysis for feature extraction.URL Hit approach for detecting and classifying
tiny urls.
• URL HTML Encoding as a lexical feature to boost our detection system on-the-fly detection of URLs
• We are using tkinter to create GUI for the application.
• In machine learning project there are two stages :- Training and prediction. There are ten models for
training and prediction.These models will be trained and saved.
FRONT END & BACK END

 Front-end :- Python
 Back-end :- Python

PYTHON:
Python is an interpreted high-level general-purpose programming language. Its
design philosophy emphasizes code readability with its use of significant indentation.
Its language constructs as well as its object-oriented approach aim to help programmers
write clear, logical code for small and large-scale projects.
MODULE DESCRIPTION

It is a machine learning project and any type of normal user can use the system.it is a desktop application

1. Preprocessing dataset
• Feature extraction using lexical features

2. Training
• Create 10 models
• Train train 10 models parallel using the extracted features
• Use output of 10 models to train second layer SVM
• Save trained models
3. Prediction
• Load URL
• Expand URL
• Extract features of URL
• Calculate output of first layer
• Calculate final result using second layer SVM

4. GUI creation
• Using tkinter (Desktop application)
• Option to enter URL
• Button to start prediction
• Option to view result in the same window
FLOW CHART
PROGRESS OF PROJECT
• Currently started coding section
• Submission of synopsis and Diagram is completed

 Synopsis :- 10-09-2021
 Diagrams :-24-09-2021
CONCLUSION
• PhishHaven is a Desktop based application designed with a purpose of detecting and prevent phishing urls.
• We can use this application to prevent the cyber crimes like email spoofing,website forging,social engineering
etc.we can build potential cybersecurity system with this project.
• By applying multi-threading technique at an input unit we can work on multiple URLs simultaneously, hence
incorporating the scalability factor in PhishHaven for classifying multiple URLs at a time.
• PhishHaven has achieved a signicant accuracy in classifying both AI-generated and human-crafted phishing
URLs.

You might also like