Performance Evaluation of Machine Learning Techniques for Identifying Forged and Phony Uniform Resource Locators (URLs)

Abstract

Since the invention of Information and Communication Technology (ICT), there has been a great shift from the erstwhile traditional approach of handling information across the globe to the usage of this innovation. The application of this initiative cut across almost all areas of human endeavours. ICT is widely utilized in education and production sectors as well as in various financial institutions. It is of note that many people are using it genuinely to carry out their day to day activities while others are using it to perform nefarious activities at the detriment of other cyber users. According to several reports which are discussed in the introductory part of this work, millions of people have become victims of fake Uniform Resource Locators (URLs) sent to their mails by spammers. Financial institutions are not left out in the monumental loss recorded through this illicit act over the years. It is worth mentioning that, despite several approaches currently in place, none could confidently be confirmed to provide the best and reliable solution. According to several research findings reported in the literature, researchers have demonstrated how machine learning algorithms could be employed to verify and confirm compromised and fake URLs in the cyberspace. Inconsistencies have however been noticed in the researchers’ findings and also their corresponding results are not dependable based on the values obtained and conclusions drawn from them. Against this backdrop, the authors carried out a comparative analysis of three learning algorithms (Naïve Bayes, Decision Tree and Logistics Regression Model) for verification of compromised, suspicious and fake URLs and determine which is the best of all based on the metrics (F-Measure, Precision and Recall) used for evaluation. Based on the confusion metrics measurement, the result obtained shows that the Decision Tree (ID3) algorithm achieves the highest values for recall, precision and f-measure. It unarguably provides efficient and credible means of maximizing the detection of compromised and malicious URLs. Finally, for future work, authors are of the opinion that two or more supervised learning algorithms can be hybridized to form a single effective and more efficient algorithm for fake URLs verification.

Keywords: Learning-algorithms, Forged-URL, Phoney-URL, performance-comparison