Network link identification method, device, storage medium and electronic equipment

Abstract

The invention discloses a network link identification method and device, a storage medium and electronic equipment, and belongs to the technical field of cloud. The method comprises the steps of obtaining a to-be-identified target URL; performing multi-granularity feature extraction on the target URL to obtain a word embedding feature, a character embedding feature and a domain name embedding feature of the target URL; performing feature fusion processing on the word embedding features and the character embedding features of the target URL; based on the obtained fusion feature sequence and domain name embedding features of the target URL, obtaining an untrusted score of the target URL; in response to the fact that the untrusted score of the target URL is greater than a target threshold, outputting a first identification result, wherein the first identification result is used for indicating that the target URL is an untrusted URL forbidden to be accessed. According to the method, no manual feature engineering is needed, semantic information and mode discrimination features in the URL text can be effectively captured, the manpower and material resource cost is reduced, and the detection accuracy of malicious URLs can be improved.

Description

technical field [0001] The present application relates to the field of cloud technology, and in particular to a network link identification method, device, storage medium and electronic equipment. Background technique [0002] In daily work and life, the existence of malicious URL (Uniform Resource Locator, Uniform Resource Locator) makes network users always suffer from the threat of network security issues. In a broad sense, malicious URLs generally refer to network links that users visit involuntarily. These network links are usually implanted with malicious codes (such as viruses). Malicious codes induce users to visit by pretending to be normal services. Once a user visits a malicious URL, he or she will face risks such as theft of personal information or loss of personal property. [0003] In order to identify malicious URLs, related technologies usually adopt a malicious URL identification scheme based on vocabulary filtering. Among them, this scheme needs to manual...

AI Technical Summary

Problems solved by technology

[0004] For the above malicious URL identification scheme, since the vocabulary feature template needs to be manually designed in advance based on experience, it is too cumbersome and time-consuming; in addition, once the URL to be identified contains words that are not involved in the vocabulary feature template, the accuracy of the recognition result The accuracy cannot be guaranteed, which will seriously affect the recognition accuracy of malicious URLs

Images