Abstract
With the market share of Android system becoming the first in the world, the security problem of Android system is becoming more and more serious. How to effectively detect Android malware has become a significant problem. Permissions and API calls in Android applications can effectively reflect the behavior patterns of an Android application. Most researchers have only considered a single permission or API feature, and did not consider associations and patterns inside the permission or API features. Some scholars have also tried to find the combination modes inside the permission features in malwares, but the detection of maliciousness according to this combination mode is too absolute. This paper proposes a malware detection method, which combines the advantages of frequent pattern mining and Naive Bayes to effectively identify Android malwares.
Highlights
The Android operating system is based on Linux and is an open source operating system developed by Google
In order to help identify Android malicious applications effectively, this paper introduces a android malicious application detection method based on frequent pattern and weighted Naive Bayes, which performs frequent pattern mining on the extracted privilege features and API features of Android applications, and use the frequent pattern as feature to identify and distinguish Android malicious applications through a weighted Naive Bayes algorithm
This paper proposes an Android malware detection method based on frequent patterns and weighted Naive Bayes, Fig. 1 shows the overall process of our approach, it works in the following step: Permission and API extraction, extracting the permission features and API call features in Android applications, and filtering according to the degree of discrimination of these features, and selecting the top 40 features with the best discrimination
Summary
Identifying and classifying the malware directly through the frequent patterns found in the rights and API features tends to have a high false positive rate This is because a large number of normal Android applications often have frequent patterns of malicious Android applications. The main contributions of this paper are as follows: We introduce the approach that performs Android malicious application detection based on frequent patterns and weighted Naive Bayes. Combine the frequent permission & API call feature and weighted Naive Bayes method to classify Android apps. Based on this Android malicious application detection method, we implement a detection tool that can effectively classify and identify whether an Android application is a malicious application or not
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
