Malicious software detection method and device, server and readable storage medium

Abstract

The invention discloses a malicious software detection method, which comprises the steps of sending a model construction command to each terminal, and obtaining model parameters of a malicious detection model of each terminal; determining an optimal model parameter according to each model parameter; and sending the optimal model parameters to each terminal, so that each terminal determines an optimal malicious detection model according to the optimal model parameters, and performs malicious software detection by using the optimal malicious detection model. The technical scheme obtains local data through each terminal to train a malicious detection model, and determines an optimal malicious detection model according to model parameters of each terminal to complete malicious software detection, wherein training of the malicious detection model is carried out in each terminal, and a server does not need to acquire local data in the terminal, so that leakage of terminal privacy is avoided,and the efficiency of model training is improved. The invention also provides a malicious software detection device, a server and a readable storage medium, which have the above beneficial effects.

Description

technical field [0001] The present application relates to the field of software detection, in particular to a method, device, server and readable storage medium for malware detection. Background technique [0002] With the development of communication technology, the application of mobile terminals, such as smart phones, tablet computers and other devices, is becoming more and more common. It can be said that they have gradually become an indispensable part of people's life. However, while these high-tech products enrich people's life and provide convenience for people's life, they also bring some information security problems. In order to achieve a certain purpose, some illegal software providers often distribute some malicious software in the network. When the user browses some malicious websites or downloads certain information, the malicious software will run in the user's terminal, and the Harassing users, and in severe cases, may leak user information such as account ...

AI Technical Summary

Problems solved by technology

However, while these high-tech products enrich people's lives and provide convenience for people's lives, they also bring about some information security issues.

In order to achieve a certain purpose, some illegal software providers often distribute some malicious software in the network. When the user browses some malicious websites or downloads certain information, the malicious software will run in the user's terminal, and the Harass users, and may leak user information such as account passwords, seriously threatening the personal and property safety of users

[0003] In the existing technology, malware detection models are usually used to detect malware. However, current malware detection models use centralized acquisition of terminal logs or traffic data to uniformly train the initial model, which may easily lead to leakage of terminal privacy.

Images