Analysis of Machine Learning Techniques on URL Phishing Dataset
The Internet has become a vital part of daily life, as do almost all online social and financial practices. However, rising phishing sites today faced significant threats because of their appallingly imperceptible danger. Phishing is an online fraudulent act that uses social engineering and technical subterfuge to trick internet users and capture their sensitive data or critical information online. There is a lack of knowledge on implementing a suitable classification technique on machine-learning tools for analyzing phishing URLs or Websites. This research aims to identify the best classification technique using the orange tool on these three datasets and implement the phishing URL analysis methodology comprising six phases. Based on the result, Decision Tree is the best classification technique for identifying the URL phishing attack. It has obtained the highest accuracy result of 88.30% and 70.70% in Dataset 2 and Dataset 3, respectively. In the future, more classification techniques or machine learning tools with different performances are explored to analyze Phishing URLs / Websites for better results.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a copyright form (JACTA) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).