Detection of malicious websites across multiple classes using n-gram features and vgg based on url analysis

SUMMARY

Checked at the time of click. The authors propose a malicious website URL classification method based on n-gram features and a VGG-style Convolutional Neural_Network (CNN). Inspired by the idea of using image recognition techniques for different tasks, the authors implement a neural_network modified from VGGNet, one of the most well-known image classification networks, to extract high-level patterns from "images" of n-gram features and perform identification of malicious URLs. Various researches of the application of neural_networks on URL classification have been conducted. As a type of recurrent neural_networks, LSTM is able to handle . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or E-mail:

If you don't have an account, you can create one here.