Malicious URL detection using multi-layer filtering model

Malicious URLs are harmful to every aspect of computer users. Detecting of the malicious URL is very important. Currently, detection of malicious webpages techniques includes black-list and white-list methodology and machine learning classification algorithms are used. However, the black-list and white-list technology is useless if a particular URL is not in list. In this paper, we propose a multi-layer model for detecting malicious URL. The filter can directly determine the URL by training the threshold of each layer filter when it reaches the threshold. Otherwise, the filter leaves the URL to next layer. We also used an example to verify that the model can improve the accuracy of URL detection.