URL Based Gateway Side Phishing Detection Method

摘要

Phishing attack has become the most dangerous form of fraud to hit online and mobile businesses. In this paper, we reveal some new aspects of the common features that appear in the phishing URLs, and introduce a statistical machine learning classifier to detect the phishing sites which relies on these selected features. Unlike previous studies, we do not utilize a single model for different regions since the result of our analysis shows that the features in different phishing domains have mismatched distributions. As it is impossible for us to recollect enough data and rebuild the models, we adjust the existing model by the transfer learning algorithm to solve these problems. A number of comprehensive experiments show that our proposed method achieves more than 93% accuracy over a balanced dataset and less than 1% error rates in the simulated real phishing scene. Moreover, the well performance in the target domain demonstrates the use of transfer learning algorithm in the anti-phishing scenario is feasible.