Malicious picture interception method, device and equipment and storage medium

Abstract

The invention discloses a malicious picture interception method and device, equipment and a storage medium, and belongs to the technical field of information safety. The method comprises the steps ofextracting an image fingerprint of a to-be-audited picture; if the similarity between the low-dimensional image fingerprint of the to-be-audited picture and the low-dimensional image fingerprint of the picture in the malicious picture library and the similarity between the high-dimensional image fingerprint of the to-be-audited picture and the high-dimensional image fingerprint of the picture in the malicious picture library meet a first condition, intercepting the to-be-audited picture; if at least one of the similarity between the low-dimensional image fingerprint of the to-be-audited picture and the low-dimensional image fingerprint of the picture in the malicious picture library and the similarity between the high-dimensional image fingerprint of the to-be-audited picture and the high-dimensional image fingerprint of the picture in the malicious picture library meets a second condition, performing character recognition on the to-be-audited picture; and when it is identified that the matching degree of the text in the to-be-audited picture and the text in the malicious text content library is higher than a threshold value, intercepting the to-be-audited picture.

Description

technical field [0001] The present application relates to the technical field of information security, and in particular, to a malicious image interception method, device, device and storage medium. Background technique [0002] In the information age, the transmission and release of information does not require strict supervision. For example, malicious pictures with malicious text are usually used to spread pornography, gambling, and marketing information. In order to avoid the spread of these pictures, it is necessary to review the pictures that users want to publish before publishing. [0003] In the Internet industry, malicious pictures published by malicious accounts are subject to frequent changes. In the process of implementing the present invention, the inventor found that the relevant technology adopts a single fingerprint extraction algorithm to intercept malicious pictures very limited, and can only intercept pictures with identical or partial content. There are...

AI Technical Summary

Problems solved by technology

[0003] In the Internet industry, malicious pictures released by malicious accounts are frequently changing. In the process of realizing the present invention, the inventor found that the relevant technology uses a single fingerprint extraction algorithm to intercept malicious pictures very limitedly, and can only intercept pictures with the same or partial content. There are a small number of different pictures in the content, and when the malicious picture changes, it cannot be accurately and effectively intercepted

Images