A Context-Aware Android Malware Detection Approach Using Machine Learning
The Android platform has become the most popular smartphone operating system, which makes it a target for malicious mobile apps. This paper proposes a machine learning-based approach for Android malware detection based on application features. Unlike many prior research that focused exclusively on A...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/13/12/563 |
| _version_ | 1827638469046829056 |
|---|---|
| author | Mohammed N. AlJarrah Qussai M. Yaseen Ahmad M. Mustafa |
| author_facet | Mohammed N. AlJarrah Qussai M. Yaseen Ahmad M. Mustafa |
| author_sort | Mohammed N. AlJarrah |
| collection | DOAJ |
| description | The Android platform has become the most popular smartphone operating system, which makes it a target for malicious mobile apps. This paper proposes a machine learning-based approach for Android malware detection based on application features. Unlike many prior research that focused exclusively on API Calls and permissions features to improve detection efficiency and accuracy, this paper incorporates applications’ contextual features with API Calls and permissions features. Moreover, the proposed approach extracted a new dataset of static API Calls and permission features using a large dataset of malicious and benign Android APK samples. Furthermore, the proposed approach used the Information Gain algorithm to reduce the API and permission feature space from 527 to the most relevant 50 features only. Several combinations of API Calls, permissions, and contextual features were used. These combinations were fed into different machine-learning algorithms to show the significance of using the selected contextual features in detecting Android malware. The experiments show that the proposed model achieved a very high accuracy of about 99.4% when using contextual features in comparison to 97.2% without using contextual features. Moreover, the paper shows that the proposed approach outperformed the state-of-the-art models considered in this work. |
| first_indexed | 2024-03-09T16:17:46Z |
| format | Article |
| id | doaj.art-75076b9a885d42b89cf5f6df6ba6f043 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-09T16:17:46Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-75076b9a885d42b89cf5f6df6ba6f0432023-11-24T15:37:11ZengMDPI AGInformation2078-24892022-11-01131256310.3390/info13120563A Context-Aware Android Malware Detection Approach Using Machine LearningMohammed N. AlJarrah0Qussai M. Yaseen1Ahmad M. Mustafa2CIS Department, Jordan University of Science and Technology, Irbid 22110, JordanCIS Department, Jordan University of Science and Technology, Irbid 22110, JordanCIS Department, Jordan University of Science and Technology, Irbid 22110, JordanThe Android platform has become the most popular smartphone operating system, which makes it a target for malicious mobile apps. This paper proposes a machine learning-based approach for Android malware detection based on application features. Unlike many prior research that focused exclusively on API Calls and permissions features to improve detection efficiency and accuracy, this paper incorporates applications’ contextual features with API Calls and permissions features. Moreover, the proposed approach extracted a new dataset of static API Calls and permission features using a large dataset of malicious and benign Android APK samples. Furthermore, the proposed approach used the Information Gain algorithm to reduce the API and permission feature space from 527 to the most relevant 50 features only. Several combinations of API Calls, permissions, and contextual features were used. These combinations were fed into different machine-learning algorithms to show the significance of using the selected contextual features in detecting Android malware. The experiments show that the proposed model achieved a very high accuracy of about 99.4% when using contextual features in comparison to 97.2% without using contextual features. Moreover, the paper shows that the proposed approach outperformed the state-of-the-art models considered in this work.https://www.mdpi.com/2078-2489/13/12/563AndroidAPI Callscontextual informationmachine learningmalwarepermissions |
| spellingShingle | Mohammed N. AlJarrah Qussai M. Yaseen Ahmad M. Mustafa A Context-Aware Android Malware Detection Approach Using Machine Learning Information Android API Calls contextual information machine learning malware permissions |
| title | A Context-Aware Android Malware Detection Approach Using Machine Learning |
| title_full | A Context-Aware Android Malware Detection Approach Using Machine Learning |
| title_fullStr | A Context-Aware Android Malware Detection Approach Using Machine Learning |
| title_full_unstemmed | A Context-Aware Android Malware Detection Approach Using Machine Learning |
| title_short | A Context-Aware Android Malware Detection Approach Using Machine Learning |
| title_sort | context aware android malware detection approach using machine learning |
| topic | Android API Calls contextual information machine learning malware permissions |
| url | https://www.mdpi.com/2078-2489/13/12/563 |
| work_keys_str_mv | AT mohammednaljarrah acontextawareandroidmalwaredetectionapproachusingmachinelearning AT qussaimyaseen acontextawareandroidmalwaredetectionapproachusingmachinelearning AT ahmadmmustafa acontextawareandroidmalwaredetectionapproachusingmachinelearning AT mohammednaljarrah contextawareandroidmalwaredetectionapproachusingmachinelearning AT qussaimyaseen contextawareandroidmalwaredetectionapproachusingmachinelearning AT ahmadmmustafa contextawareandroidmalwaredetectionapproachusingmachinelearning |