Hybrid feature screening method for Android malicious software detection

Abstract

The invention discloses a hybrid feature screening method for Android malicious software detection. The method comprises the steps that a training set and a test set are generated according to existing data; a primary feature subset is screened out; an optimal feature subset corresponding to each type of classifiers is obtained; and the optimal feature subset is utilized to train the correspondingclassifiers. Through the hybrid feature screening method for Android malicious software detection, the optimal feature subset and a classification algorithm matched with the optimal feature subset can be screened out, modeling time of the classifiers is greatly shortened, and the detection efficiency and detection precision of Android malicious software detection can be improved.

Description

technical field [0001] The invention relates to the technical field of software security, in particular to a mixed feature screening method for Android malware detection. Background technique [0002] According to the latest statistics from the market research company Strategy Analytics, in the third quarter of 2016, the global market share of Android reached a record 87.5%, while the global market share of iOS fell to 12.1%, mainly due to the openness of the Android system. However, the openness also leads to the proliferation of Android malware, and these malware (such as spyware, scareware, and adware, etc.) have brought serious security threats to users. The increasingly severe security situation of Android mobile phones makes how to detect Android malware quickly and efficiently become a current research hotspot. [0003] Because machine learning has the ability to process data on a large scale and can make judgments on targets in similar data structures, many research...

AI Technical Summary

Problems solved by technology

However, the screening algorithm cannot guarantee the size of the feature subset, and the screening effect is difficult to guarantee, so its classification accuracy is not high

[0010] To sum up, the current detection research results using machine learning algorithms are relatively mature, but the common Android malware detection methods still have many deficiencies in feature screening, and the solution to these problems will inevitably require the study and improvement of feature screening algorithms

Images