Machine Learning-Based Malicious URLs Detection

Abstract

Malicious URL’s also known as harmful website which is a serious and common thread to network security. World Wide Web (WWW) (Vanhoenshoven et al. in 2016 IEEE symposium series on computational intelligence (SSCI). IEEE, 2016 [1]), which encourages a wide range of illicit actions like financial fraud, malware distribution and e-commerce. It is of vital importance to discover and act on different ventures on time. Several procedures like blacklisting have been carried out to detect malicious Uniform Resource Locators (URLs) (Catak et al. in Malicious URL detection using machine learning. IGI Global, 2021 [2]). To advance the majority of harmful Uniform Resource Locator’s, different machine learning algorithms are executed in the modern years. Here, in this research paper, we are addressing malicious URLs detection as a problem of classification and also to understand the working and functioning of known machine learning classifiers, namely support vector machines (SVMs), K-nearest neighbors (KNNs), random forest (RF) and Naive Bayes (Vanhoenshoven et al. in 2016 IEEE symposium series on computational intelligence (SSCI). IEEE, 2016 [1]). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.