| Title | Identification and Analysis of Phishing Website based on Machine Learning Methods |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Alkawaz, Mohammed Hazim, Joanne Steven, Stephanie, Mohammad, Omar Farook, Gapar Md Johar, Md |
| Conference Name | 2022 IEEE 12th Symposium on Computer Applications & Industrial Electronics (ISCAIE) |
| Date Published | may |
| Keywords | Decision Tree, Decision trees, feature extraction, Human Behavior, hybrid, Industrial electronics, machine learning, machine learning algorithms, phishing, Phishing Detection, pubcrawl, Random Forest, Resource description framework, Resource Description Framework (RDF), security, visual similarity, Web pages |
| Abstract | People are increasingly sharing their details online as internet usage grows. Therefore, fraudsters have access to a massive amount of information and financial activities. The attackers create web pages that seem like reputable sites and transmit the malevolent content to victims to get them to provide subtle information. Prevailing phishing security measures are inadequate for detecting new phishing assaults. To accomplish this aim, objective to meet for this research is to analyses and compare phishing website and legitimate by analyzing the data collected from open-source platforms through a survey. Another objective for this research is to propose a method to detect fake sites using Decision Tree and Random Forest approaches. Microsoft Form has been utilized to carry out the survey with 30 participants. Majority of the participants have poor awareness and phishing attack and does not obverse the features of interface before accessing the search browser. With the data collection, this survey supports the purpose of identifying the best phishing website detection where Decision Tree and Random Forest were trained and tested. In achieving high number of feature importance detection and accuracy rate, the result demonstrates that Random Forest has the best performance in phishing website detection compared to Decision Tree. |
| DOI | 10.1109/ISCAIE54458.2022.9794467 |
| Citation Key | alkawaz_identification_2022 |
Identification and Analysis of Phishing Website based on Machine Learning Methods