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

Malicious Files Detection using Machine Learning

Author(s):

Nisha Chaudhary , B.K Birla College of Arts, Science and Commerce (Autonomous)

Keywords:

Malicious Files, Machine Learning

Abstract

In a comprehensive study on malware detection, we evaluated five machine learning models: multinomial naive bayes, random forest classifiers, K-nearest neighbours, decision tree classifiers, and support vector classifiers, using a diverse dataset with file feature extraction. Results showcased varying performances, with the Random Forest Classifier standing out with a flawless accuracy score of 1.00, excelling in distinguishing between malware and legitimate files. The Decision Tree Classifier and K-Nearest Neighbours Classifier followed closely, both achieving a high accuracy of 0.99. This research underscores the effectiveness of machine learning models, especially Random Forest, in enhancing cybersecurity by accurately identifying potential threats amidst digital files.

Other Details

Paper ID: IJSRDV11I80044
Published in: Volume : 11, Issue : 8
Publication Date: 01/11/2023
Page(s): 76-78

Article Preview

Download Article