A webpage backdoor detection method and system based on data executable features

Abstract

The invention discloses a webpage backdoor detection method based on data executable features. The webpage backdoor detection method comprises the steps of obtaining a sample source code training setand a to-be-tested source code; performing opcode code extraction and word frequency feature extraction on each sample source code in the sample source code training set and the to-be-tested source code in sequence; performing data executable feature extraction on each sample source code in the sample source code training set and the to-be-tested source code to obtain data executable features of each sample source code and the to-be-tested source code; constructing feature matrixes corresponding to the sample source codes and the to-be-tested source code respectively; performing webpage backdoor detection training on the feature matrixes corresponding to the sample source codes to obtain a webpage backdoor detection model; and inputting the feature matrix corresponding to the to-be-testedsource code into the webpage backdoor detection model for webpage backdoor detection. The invention further discloses a storage medium and a system. According to the invention, the accuracy of webpagebackdoor detection can be effectively improved, and misinformation is reduced.

Description

technical field [0001] The invention belongs to the technical field of network security, and in particular relates to a web page backdoor detection method and system based on data executable features. Background technique [0002] With the rapid development of the Internet and the rapid popularization of web applications, web service attacks have become more frequent, and implanting web page backdoors into target sites has become one of the most commonly used attack methods for attackers. Attackers use web page backdoors to obtain system information. Command execution environment, so as to further control the website server, to achieve the purpose of information sniffing, data theft or tampering. In order to combat web service attacks, the research on web backdoor detection has become one of the current important tasks. [0003] Webpage backdoor detection technology is currently divided into two methods: dynamic feature detection and static feature detection. Among them, dy...

AI Technical Summary

Problems solved by technology

Since statistical features can only be detected and analyzed from an overall point of view, due to the rapid development of current Web services, developers often obfuscate and encrypt the source code in order to avoid source code leakage, which leads to methods based on statistical features to detect web pages. A large number of false positives are generated during the backdoor, and effective detection and analysis cannot be carried out

Images