Accuracy of Machine Learning for Classifying Malicious URL

Muhammad Risaldi; Satria Gunawan Zain; Jumadi Mabe Parenreng

doi:10.1109/COMNETSAT59769.2023.10420801

Accuracy of Machine Learning for Classifying Malicious URL

Closed

Muhammad Risaldi, Satria Gunawan Zain, Jumadi Mabe Parenreng

2023 Proceeding - COMNETSAT 2023: IEEE International Conference on Communication, Networks and Satellite Conference paper Cited by 1

Abstract

Malicious URLs are a common issue in society, and many people are unaware of the differences between malicious and safe URLs. This lack of awareness leads to data breaches and makes it easier for malware to infiltrate the victim devices. In this paper, we propose the use of machine learning to classify malicious URLs. In addition to demonstrating the accuracy achieved using machine learning in this study, we compared the accuracy levels of several machine learning models in classifying malicious URLs.In this study, we employed four machine learning models to determine the best model for classifying malicious URLs. To facilitate this comparison, we used evaluation metrics, such as accuracy, precision, recall, and F1-score. The results of this study indicate that machine learning is an effective method for detecting malicious URLs with a high level of accuracy. Of the four models used, Extra Trees emerged as the best model for classification, achieving a total accuracy rate of 91.46%. © 2023 IEEE.

Affiliations

State University of Makassar, Computer Enginering, Makassar, Indonesia

View full text (DOI) →

Research at a Glance

Research at a Glance

Topics & SDG Alignment

Collaboration

Author Profile (Selected)

References Overview

Journal & Source

Metadata & Integrity