Skip to content

Latest commit

 

History

History
104 lines (53 loc) · 3.69 KB

README.md

File metadata and controls

104 lines (53 loc) · 3.69 KB

Phishing Website Detection

Python scikit-learn Azure Flask

Model

About

This project is developed as part of the iNeuron.ai internship. The primary objective of this project is to build a model using Machine Learning which can accurately predict whether a website is phishing or safe.

Description

Phishing is an attempt of fraudulently accessing sensitive or confidential information of an internet user by appearing as a trusted person or entity. It is a social engineering attack that aims at exploiting the weakness found in system processes as caused by system users.

Features

  • Website URL analysis for phishing indicators.
  • Machine learning model integration for accurate phishing detection.
  • Web interface for easy interaction (Entering features manually gives an accuracy of 96.2%)

Data Description

https://data.mendeley.com/datasets/72ptz43s9v/1

Technologies Used

Database used:

MySQL

Machine Learning Libraries

image image-6 image-7

For Feature Selection : Yellowbrick by Scikit Learn

image-8

IDE:

For building Random Forest Classifier model

Jupyter Notebook

For end-to-end project

Visual Studio Code

Deployment :

image-10

image-12

This ML feature is deployed by creating a Flask frontend and as static web app using Azure.

The model achieved after hyperparameter tuning had following parameters:

RandomForestClassifier(max_depth=20, min_samples_leaf=2, min_samples_split=13, n_estimators=105)

Accuracy Achieved

Classification Report using Yellowbrick

image-11



## Initialize the Git Repositry
``` git init

git add .
    
git commit -m "Initial commit"
    
git branch -M main
    
git remote add origin <github_url>
    
git push -u origin main

To modify on github


 git commit -m "proper message"
 
 git push -u origin main

External Links

Azure Static Web Apps