High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Malicious URLs Detection using Lexical Features based on Machine Learning

Author(s):

Aarti Dhotre , B.K Birla College of Arts, Science and Commerce (Autonomous) Kalyan

Keywords:

Malicious URL, Machine Learning Algorithms, Feature Selection, Cross-Validation

Abstract

Cybercriminals continually exploit malicious URLs in emails, messages, and pop-ups to propagate cyberattacks, deceiving users into downloading the malware into their system. This research aims to create an efficient and effective system for detecting malicious URLs using only Lexical features extracted from the URLs. Four machine learning algorithms, namely Support Vector Machine (SVM), Random Forest, Decision Trees, and K-Nearest, are explored for the classification of URLs as benign or malicious. Performance is evaluated using accuracy, precision, recall, and F1-score metrics. The findings indicate that Random forest and decision Tree models excel in malicious URL detection.

Other Details

Paper ID: IJSRDV11I80022
Published in: Volume : 11, Issue : 8
Publication Date: 01/11/2023
Page(s): 36-38

Article Preview

Download Article