The Comparative Analysis of Machine Learning Algorithms for Phishing Attack Detection

Volume 18, Issue 2,  2024

Download

< /tr>
Author(s):

Almina Sehrish SZABIST University, Pakistan, alminasehrish88@gmail.com

Muhammad Raza* SZABIST University, Gharo Campus, Pakistan, razacom_2000@yahoo.com

Muhammad Faizan Khan IQRA University, Karachi, Pakistan, faizanonline86@gmail.com

Sabih Hida SZABIST University, Pakistan, sabihhida@hotmail.com

Rageshwari Haryani SZABIST University, Pakistan , rageshwariharyani1997@gmail.com

Abstract Due to the internet's indispensable role in day-to-day operations, cybercrimes have increased dramatically, with phishing being a serious concern. Phishing attacks employ phony websites to obtain sensitive data and user passwords. Because hackers are always trying to change their strategies wisely, traditional preventative measures like software detection and user awareness frequently fall short. With their capacity for self-learning, machine learning-based solutions provide a more potent protection. Using a supervised learning framework, this thesis offers a thorough review of machine learning techniques for phishing detection. making use of a dataset that has 87 attributes. Runtime, train accuracy, test accuracy, precision, recall, and F1-score are used to assess the efficiency of various algorithms, such as Random Forest, Decision Trees, SVM, Naive Bayes, K-Nearest Neighbors (KNN), XGBoost, Boosted Decision Tree, AdaBoost, Extra Trees, LightGBM, and CatBoost. With a 97.33% test accuracy as well as outstanding recall, precision, and F1-score, XGBoost stands out. Powerful performance is also demonstrated by Random Forest and LightGBM, demonstrating their effectiveness in identifying phishing attempts. This study feeds future research on optimization tactics and ensemble approaches to improve detection robustness and accuracy, and it gives cybersecurity professionals effective insights for better phishing detection.
Keywords Phishing Detection, Machine Learning Algorithms, Supervised Learning, URL Analysis, Feature Extraction, Cybersecurity
Year 2024
Volume 18
Issue 2
Type Research paper, manuscript, article
Journal Name Journal of Information & Communication Technology
Publisher Name ILMA University
Jel Classification -
DOI -
ISSN no (E, Electronic) 2075-7239
ISSN no (P, Print) 2415-0169
Country Pakistan
City Karachi
Institution Type University
Journal Type Open Access
Manuscript Processing Blind Peer Reviewed
Format PDF
Paper Link https://jict.ilmauniversity.edu.pk/journal/jict/18.2/4.pdf
Page 22-30