URL Based Phishing Website Detection using Machine Learning Models
URL Based Phishing Website Detection using Machine Learning Models
OUR PROPOSED PROJECT ABSTRACT:
Phishing attacks have emerged as a significant threat to online security, posing risks to both individuals and organizations. The development of efficient detection mechanisms is crucial to mitigate these threats. This project, titled “URL Based Phishing Website Detection using Machine Learning Models,” presents a comprehensive approach to identify phishing websites based on their URLs.
The project leverages the power of machine learning models, implemented in MATLAB, to enhance the accuracy of phishing website detection. Two prominent algorithms, Support Vector Machine (SVM) and Random Forest, were employed to achieve robust results.
The SVM model exhibited remarkable performance, achieving an impressive accuracy rate of 100%. SVM is renowned for its ability to classify data points accurately, making it an ideal choice for binary classification tasks like phishing website detection. Its utilization in this project highlights its effectiveness in accurately distinguishing between legitimate and malicious URLs.
Additionally, the Random Forest algorithm was employed, yielding a commendable accuracy rate of 96.97%. Random Forest, a robust ensemble learning method, excels in handling complex and noisy data. Its performance underscores its suitability for the task of phishing website detection.
The project’s success lies not only in the choice of machine learning algorithms but also in the meticulous data preprocessing, feature engineering, and model tuning processes. These efforts collectively contribute to the outstanding accuracy achieved in phishing website detection.
In summary, this project demonstrates the efficacy of machine learning models, particularly SVM and Random Forest, in the domain of URL-based phishing website detection. The achieved accuracies of 100% and 96.97% underscore the potential of these models to significantly enhance online security by effectively identifying and mitigating phishing threats. The methodologies and insights presented in this project can serve as a valuable foundation for future developments in the field of cybersecurity.
PROJECT OUTPUT VIDEO:
ALGORITHM/ MODEL USED:
Support Vector Machine (SVM) and Random Forest
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
SOFTWARE REQUIREMENTS:
- Operating system : Windows 10 Pro.
- Coding Language : MATLAB
- Tool : MATLABR2021A
REFERENCE:
ABDUL KARIM, MOBEEN SHAHROZ, KHABIB MUSTOFA, SAMIR BRAHIM BELHAOUARI, AND S. RAMANA KUMAR JOGA, “Phishing Detection System Through Hybrid Machine Learning Based on URL”, IEEE Access (Volume: 11), 2023.
