filmov
tv
Phishing Website Detection Project | Machine learning | Classification Models | Python
Показать описание
Project abstract:
Phishing websites create a serious risk to internet users by exposing personal information through fake emails, texts, phone calls, or websites that try to trick users into sharing personal information. To protect users from identity theft and cyberattacks, it is critical to identify these phishing sites. We explore the use of machine learning algorithms to automatically identify phishing websites to enhance online security and protect user privacy. This project aims to develop a machine learning-based approach for detecting phishing websites based on the URL. We have utilized the Phishing Websites dataset taken from the source UCI Machine learning repository, it comprises 11,055 instances, each characterized by 30 features including having_ip_address, url_length, having_at_symbol, and more. we have considered the top 10 features using the selectKBest method and The dataset is formatted in ARFF (Attribute-Relation File Format), a widely used format for representing data with attributes and their corresponding values. Three supervised machine learning models are implemented in this study: Decision Tree, Random Forest, and Support Vector Classifier(SVC) for the classification into phishing or normal websites. The three algorithms have been selected due to their better understanding and better fit for the dataset. The results of the experiments indicate that the Random Forest has the highest accuracy (94.4%) when compared to the other models, the accuracy for the Decision Tree model (94.4%), and the lowest accuracy (93.79%) for the SVC model. Considering the results closely, we find that the Random Forest and SVC algorithms perform better, particularly when looking at the Area under the Curve (AUC) as 99%.
Phishing websites create a serious risk to internet users by exposing personal information through fake emails, texts, phone calls, or websites that try to trick users into sharing personal information. To protect users from identity theft and cyberattacks, it is critical to identify these phishing sites. We explore the use of machine learning algorithms to automatically identify phishing websites to enhance online security and protect user privacy. This project aims to develop a machine learning-based approach for detecting phishing websites based on the URL. We have utilized the Phishing Websites dataset taken from the source UCI Machine learning repository, it comprises 11,055 instances, each characterized by 30 features including having_ip_address, url_length, having_at_symbol, and more. we have considered the top 10 features using the selectKBest method and The dataset is formatted in ARFF (Attribute-Relation File Format), a widely used format for representing data with attributes and their corresponding values. Three supervised machine learning models are implemented in this study: Decision Tree, Random Forest, and Support Vector Classifier(SVC) for the classification into phishing or normal websites. The three algorithms have been selected due to their better understanding and better fit for the dataset. The results of the experiments indicate that the Random Forest has the highest accuracy (94.4%) when compared to the other models, the accuracy for the Decision Tree model (94.4%), and the lowest accuracy (93.79%) for the SVC model. Considering the results closely, we find that the Random Forest and SVC algorithms perform better, particularly when looking at the Area under the Curve (AUC) as 99%.
0:12:53
Detection of Phishing Websites Using Machine Learning | Python Final Year IEEE Project
0:25:33
Detection of Phishing Websites Using Machine Learning | Python Final Year IEEE Project 2023
0:16:16
Phishing Websites Detection System using Machine Learning Techniques | IEEE Machine Learning Project
0:00:34
Phishing URL Detection Demo - Python Project
0:13:04
URL Based Phishing Website Detection using Machine Learning Models | MATLAB Final Year Project
0:00:47
Phishing URL/Links/SMS/Website/Message Detection | Machine Learning | Cyber Security |Python Project
0:01:18
Phishing Website ( URL ) Detection | Machine Learning | Flask Framework | Final Year College Project
0:04:32
Detection of Phishing Websites Using Machine Learning | Python Final Year IEEE Project 2024
0:07:18
Detecting E-Banking Phishing Websites PHP
0:01:48
Phishing URL Detection using Machine Learning | Machine Learning Projects for Final Year CSE 2024
0:06:45
Detection of Phishing Websites Using Machine Learning | Python Final Year Project 2024
0:14:47
Phishing Website Detection by Machine Learning Techniques
0:04:06
Create a phishing site in 4 minutes?? | Suprisingly easy and convenient
0:07:57
Phishing Websites Detection Using Machine Learning Algorithms
0:05:16
Detecting Phishing Websites using Machine Learning Technique
0:06:14
Phishing website detection using feature selection and machine learning
0:06:00
Detecting E Banking Phishing Websites Using Associative Classification PHP
0:03:32
AE013 | Phishing Website Detection
0:05:01
Phishing Website detection
0:01:59
Phishing Website detection
0:37:24
Phishing Sites Prediction Using Machine Learning
0:06:48
Phishing Explained In 6 Minutes | What Is A Phishing Attack? | Phishing Attack | Simplilearn
0:00:24
extension to detect phishing website| ML model | Cyber security|
0:13:06
Website Phishing Detection Tool Using URL_Final Year Project_CI180005_Tool Presentation
Комментарии