A Novel Architecture for Detecting Phishing Webpages using Cost-based Feature Selection

Phishing is one of the luring techniques used to exploit personal information. A phishing webpage detection system (PWDS) extracts features to determine whether it is a phishing webpage or not. Selecting appropriate features improves the performance of PWDS. The performance criteria are detection accuracy and system response time. The major time consumed by PWDS arises from feature extraction, which is considered as feature cost in this paper. Here, two novel features are proposed. They use the semantic similarity measure to determine the relationship between the content and the URL of a page. Since the suggested features do not apply third-party services such as search engine result, the feature extraction time decreases dramatically. Login form pre-filer is utilized to reduce unnecessary calculations and false positive rate. In this paper, a cost-based feature selection is presented as the most effective feature. The selected features are employed in the suggested PWDS. The extreme learning machine algorithm is used to classify webpages. The experimental results demonstrate that the suggested PWDS achieves a high accuracy of 97.6% and a short average detection time of 120.07 ms