Multi-malicious-software hybrid detection method, system and device with privacy protection

Abstract

The invention belongs to the technical field of malicious software detection, and discloses a multi-malicious-software hybrid detection method, system and device with privacy protection. The third party generates a public and private key pair according to a homomorphic encryption algorithm, and publishes a public key; the client collects behavior data of software used by the user group, carries out preliminary calculation, encrypts the behavior data by using a third-party public key, adds the behavior data to the generated random number and then uploads a result to the server; the server usesa reputation evaluation algorithm to complete calculation of different software reputation values by using homomorphic properties and interacting decryption with a third party according to the uploaded user group encryption data, and determines a software detection sequence according to the software reputation values; during detection, the server sequentially calls API use frequency data acquiredby decompilation software APK from the client according to a sequence; static detection is performed on the software according to the static learning model; if the detection result is non-malicious,related encrypted data and a public key thereof are called according to the system collected by the client, and real-time detection is performed by utilizing homomorphic properties and the dynamic learning model.

Description

technical field [0001] The invention belongs to the technical field of malicious software detection, and in particular relates to a privacy-protected multi-malware mixed detection method, system and device. Background technique [0002] At present, the closest existing technology: mobile malware refers to the existence of eavesdropping on user calls, stealing user information, destroying user data, unauthorized use of paid services, sending Spam information, push advertisements or fraudulent information, affect the operation of mobile terminals, endanger Internet network security and other malicious acts of application software. With the popularization of smartphones and the vigorous development of the mobile application industry, mobile malware has flooded into the application market in large numbers. Mobile malware often introduces security vulnerabilities into mobile devices, causing financial losses to users, and causing privacy leaks and other issues. Therefore, estab...

AI Technical Summary

Problems solved by technology

[0008] (1) There is a lack of solutions in the prior art that can effectively detect whether an application is malicious before installation and in real-time operation

[0009] (2) The existing technology does not consider the priority of detection. For popular and widely used software, in order to prevent damage caused by malicious behavior, it should be detected first whether it is malicious

[0010] (3) The existing technology does not consider the user's privacy protection in the cloud server malware detection process

[0012] The difficulty of the above-mentioned technical problems lies in determining an effective detection scheme before the application is installed and used and in real-time operation, how to determine the detection priority to reduce the damage caused by malicious applications, and how to protect the user's privacy during the entire detection process

Images