RNN-based malicious software detection method on cloud platform

Abstract

The invention relates to an RNN-based malicious software detection method on a cloud platform, and belongs to the field of information security. The method sequentially comprises the following steps:extracting an API calling sequence based on a time sequence, preprocessing API sequence data, constructing an RNN-based malicious software detection model, and training the RNN-based detection model.According to the method, the selected feature vector is the API call sequence of the software, the semantic attribute of the API is considered, semantic recognition of the API call sequence of the software is more accurate, and the feature is input into the bidirectional LSTM neural network model, so that the detection efficiency is effectively improved, the detection accuracy is greatly improved,the depth of the network model designed by the invention is proper, and parameters needing to be trained in the model are moderate, so that the generalization ability of the detection model is improved to a certain extent.

Description

technical field [0001] The invention relates to the field of information security, in particular to a malware detection method running on a cloud platform. Background technique [0002] In today's society, people rely more and more on smartphones, and there are more and more personal privacy information hidden in smartphones. This information is related to the safety of people's lives and property, and is therefore attacked by malware. In the field of traditional malware detection, detection based on fixed features has become more and more difficult. Therefore, in recent years, researchers have used artificial intelligence technology to detect malware and achieved certain results. However, in the initial stage of malware detection research and development, the more commonly used methods were based on the host, and with the development of the Internet, the number of malware and variant technologies continued to increase, and the host-based system became It is very bloated an...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of low accuracy of traditional detection methods and inefficiency of conventional detection systems, the present invention proposes a malware detection method running on a cloud platform to improve detection efficiency while ensuring detection accuracy

To solve the problems of low detection efficiency and insufficient detection accuracy caused by the rapid increase of malware types, and protect users' personal privacy and property safety

Images