Malicious URL detection method based on URL imaging technology

Abstract

The invention discloses a malicious URL detection method based on a URL imaging technology, and the method comprises the following steps: collecting a URL character string, and carrying out the hash processing of the URL character string; encoding the URL character string subjected to hash processing by using an ASCII code, and normalizing the encoded URL character string; converting the URL character string into a two-dimensional image by adopting a Grignard angle field according to the normalized URL character string; forming an inception CNN network according to the convolutional neural network, and training the inception CNN network; and inputting the two-dimensional image into the trained inception CNN network to obtain a judgment result of the malicious URL. By converting the URL into the two-dimensional image, the malicious URL can be accurately identified.

Description

technical field [0001] The invention belongs to the field of URL identification, and in particular relates to a malicious URL detection method based on URL imaging technology. Background technique [0002] The popularization of information technology has greatly promoted the development of online banking, e-commerce and social networks. More and more people complete social networking, shopping, and information acquisition through the Internet. The government is also promoting e-government through the Internet to enhance government transparency. and improve the quality of public decision-making. But at the same time, the Internet has also become an active platform for criminals, and a large number of cyber crimes have emerged. Cyber ​​attackers make illegal profits through phishing sites, spam ads, and malware promotions. Among these attacks, a considerable part is realized by means of malicious URLs. URL is the uniform resource locator, which is a concise representation o...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the above-mentioned deficiencies in the prior art, a method for detecting malicious URL based on URL imaging technology provided by the present invention solves the existing problems in existing malicious URL detection

Images