BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android Devices
Android has become the leading operating system for mobile devices, and the most targeted one by malware. Therefore, many analysis methods have been proposed for detecting Android malware. However, few of them use proper datasets for evaluation. In this paper, we propose BrainShield, a hybrid malwar...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/23/2948 |
| _version_ | 1797507908976508928 |
|---|---|
| author | Corentin Rodrigo Samuel Pierre Ronald Beaubrun Franjieh El Khoury |
| author_facet | Corentin Rodrigo Samuel Pierre Ronald Beaubrun Franjieh El Khoury |
| author_sort | Corentin Rodrigo |
| collection | DOAJ |
| description | Android has become the leading operating system for mobile devices, and the most targeted one by malware. Therefore, many analysis methods have been proposed for detecting Android malware. However, few of them use proper datasets for evaluation. In this paper, we propose BrainShield, a hybrid malware detection model trained on the Omnidroid dataset to reduce attacks on Android devices. The latter is the most diversified dataset in terms of the number of different features, and contains the largest number of samples, 22,000 samples, for model evaluation in the Android malware detection field. BrainShield’s implementation is based on a client/server architecture and consists of three fully connected neural networks: (1) the first is used for static analysis and reaches an accuracy of 92.9% trained on 840 static features; (2) the second is a dynamic neural network that reaches an accuracy of 81.1% trained on 3722 dynamic features; and (3) the third neural network proposed is hybrid, reaching an accuracy of 91.1% trained on 7081 static and dynamic features. Simulation results show that BrainShield is able to improve the accuracy and the precision of well-known malware detection methods. |
| first_indexed | 2024-03-10T04:55:08Z |
| format | Article |
| id | doaj.art-49cf9b1663044b66bb7a8c21a4bee028 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T04:55:08Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-49cf9b1663044b66bb7a8c21a4bee0282023-11-23T02:16:33ZengMDPI AGElectronics2079-92922021-11-011023294810.3390/electronics10232948BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android DevicesCorentin Rodrigo0Samuel Pierre1Ronald Beaubrun2Franjieh El Khoury3Mobile Computing and Networking Research Laboratory (LARIM), Department of Computer and Software Engineering, Polytechnique Montreal, Montreal, QC H3T 1J4, CanadaMobile Computing and Networking Research Laboratory (LARIM), Department of Computer and Software Engineering, Polytechnique Montreal, Montreal, QC H3T 1J4, CanadaDepartment of Computer Science and Software Engineering, Laval University, Pavillon Adrien-Pouliot, Quebec, QC G1V 0A6, CanadaMobile Computing and Networking Research Laboratory (LARIM), Department of Computer and Software Engineering, Polytechnique Montreal, Montreal, QC H3T 1J4, CanadaAndroid has become the leading operating system for mobile devices, and the most targeted one by malware. Therefore, many analysis methods have been proposed for detecting Android malware. However, few of them use proper datasets for evaluation. In this paper, we propose BrainShield, a hybrid malware detection model trained on the Omnidroid dataset to reduce attacks on Android devices. The latter is the most diversified dataset in terms of the number of different features, and contains the largest number of samples, 22,000 samples, for model evaluation in the Android malware detection field. BrainShield’s implementation is based on a client/server architecture and consists of three fully connected neural networks: (1) the first is used for static analysis and reaches an accuracy of 92.9% trained on 840 static features; (2) the second is a dynamic neural network that reaches an accuracy of 81.1% trained on 3722 dynamic features; and (3) the third neural network proposed is hybrid, reaching an accuracy of 91.1% trained on 7081 static and dynamic features. Simulation results show that BrainShield is able to improve the accuracy and the precision of well-known malware detection methods.https://www.mdpi.com/2079-9292/10/23/2948android deviceBrainShieldhybrid modelmachine learningmalware detectionOmnidroid |
| spellingShingle | Corentin Rodrigo Samuel Pierre Ronald Beaubrun Franjieh El Khoury BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android Devices Electronics android device BrainShield hybrid model machine learning malware detection Omnidroid |
| title | BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android Devices |
| title_full | BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android Devices |
| title_fullStr | BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android Devices |
| title_full_unstemmed | BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android Devices |
| title_short | BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android Devices |
| title_sort | brainshield a hybrid machine learning based malware detection model for android devices |
| topic | android device BrainShield hybrid model machine learning malware detection Omnidroid |
| url | https://www.mdpi.com/2079-9292/10/23/2948 |
| work_keys_str_mv | AT corentinrodrigo brainshieldahybridmachinelearningbasedmalwaredetectionmodelforandroiddevices AT samuelpierre brainshieldahybridmachinelearningbasedmalwaredetectionmodelforandroiddevices AT ronaldbeaubrun brainshieldahybridmachinelearningbasedmalwaredetectionmodelforandroiddevices AT franjiehelkhoury brainshieldahybridmachinelearningbasedmalwaredetectionmodelforandroiddevices |