Comparative Analysis of the Performance of Selected Learning Algorithms for Verification of vulnerable and Compromised Uniform Resource Locators (URLs)
No Thumbnail Available
Int. Sci. Technol. J. Namibia
The fact that cybercriminals have caused serious havoc and unprecedented financial loss through internet activities is well acknowledged by internet users across the globe. Different nefarious activities of the internet fraudsters have undoubtedly resulted in monumental loss of life and property of immeasurable values. From available literatures, many people have become victims of their handiworks by giving feedback to fake and phony Uniform Resource Locators (URLs) sent to their electronic mails. In the recent works by researchers in the area of cybersecurity, it has been established that machine learning approaches have been proposed to identify various compromised and fake URLs in order to safeguard internet users from becoming victim. Consequently, discrepancies noted in some the available results give room for doubt and reliability of the results obtained in their experimentations. In an attempt, however to protect internet users from experiencing further loss and to establish the performances of these algorithms, the authors carried out a comparative analysis of three learning algorithms (Na¨ıve Bayes, Decision Tree and Logistics Regression Model) for verification of compromised, phony and fake URLs and determined which is the best of all the three based on the metrics (F-Measure, Precision and Recall) used for evaluation. After the experimentation, it was finally observed that the decision tree provides optimal and efficient solution of all the tree algorithms with full and absolute F-Measure when 0.6 is considered as boundary. With optimal solution provided by the decision tree, internet users can be given reliable information and consequently be guarded against further attacks.
Algorithms, Vulnerable URL, Compromised URL, performance analysis, metrics, cybercriminals, victims, optimal solution
N.A Azeez, A.D Ajayi and C.O Yinka-Banjo (2018) “Comparative Analysis of the performance of Learning Algorithms for Verification of Vulnerable and Compromised URLs” International Science and Technology Journal of Namibia (ISTJN), University of Namibia, ISTJN 2018, vol.12, pp 3-17.