In e-commerce and e-banking environments, one of the most risks or challenges which must be considered, is the risk of online fraud specially phishing attacks. In this study, we use some visual and technical identifies of a phishing web site as parameters to implement an expert system to diagnose this type of attack in electronic banking. In the proposed system, we use 27 different features as the expert system parameter in assessing a web page, which has been classified into six parts. The artificial neural network is used to determine the weight of some of these parameters. By combination of values which could be extracted for each of these parameters, we design the system knowledge base. The inference engine of the expert system shell has used to determine the result of each part of input parameters. Finally, the results of each part compared with others to evaluate and output the result as the final inference system is provided. Based on studies conducted on several real samples of phishing web sites, the results showed that the proposed system has relatively good result to detect such attacks.
Rights and permissions | |
This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0) |