Deep Learning based Malware Detection for Android Systems: A Comparative Analysis
Nowadays, cyber attackers focus on Android, which is the most popular open-source operating system, as main target by applying some malicious software (malware) to access users' private information, control the device, or harm end-users. To detect Android malware, security experts have offered...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
2023-01-01
|
| Series: | Tehnički Vjesnik |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/433793 |
| _version_ | 1797206548443824128 |
|---|---|
| author | Esra Calik Bayazit Ozgur Koray Sahingoz Buket Dogan |
| author_facet | Esra Calik Bayazit Ozgur Koray Sahingoz Buket Dogan |
| author_sort | Esra Calik Bayazit |
| collection | DOAJ |
| description | Nowadays, cyber attackers focus on Android, which is the most popular open-source operating system, as main target by applying some malicious software (malware) to access users' private information, control the device, or harm end-users. To detect Android malware, security experts have offered some learning-based models. In this study, we developed an Android malware detection system that uses different machine\deep learning models by performing both dynamic analyses, in which suspected malware is executed in a safe environment for observing its behaviours, and static analysis, which examines a malware file without any execution on the Android device. The benefits and weaknesses of these models and analyses are described in detail in this comparative study, and directions for future studies are drawn. Experimental results showed that the proposed models gave better results than those in the literature, with 0.988 accuracy for LSTM on static analysis and 0.953 accuracy for CNN-LSTM on dynamic analysis. |
| first_indexed | 2024-04-24T09:08:46Z |
| format | Article |
| id | doaj.art-dfdbd99b08434feba89584fcedaaabf7 |
| institution | Directory Open Access Journal |
| issn | 1330-3651 1848-6339 |
| language | English |
| last_indexed | 2024-04-24T09:08:46Z |
| publishDate | 2023-01-01 |
| publisher | Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek |
| record_format | Article |
| series | Tehnički Vjesnik |
| spelling | doaj.art-dfdbd99b08434feba89584fcedaaabf72024-04-15T18:25:50ZengFaculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in OsijekTehnički Vjesnik1330-36511848-63392023-01-0130378779610.17559/TV-20220907113227Deep Learning based Malware Detection for Android Systems: A Comparative AnalysisEsra Calik Bayazit0Ozgur Koray Sahingoz1Buket Dogan21) Computer Engineering Department, Fatih Sultan Mehmet Vakif University, Beyoglu, Istanbul, 34445, Turkey 2) Marmara University Institute of ScienceComputer Engineering Department, Biruni University, Topkapi, Istanbul, 34093, TurkeyDepartment of Computer Engineering, Faculty of Technology, Marmara University, Basibuyuk, Istanbul, 34854, TurkeyNowadays, cyber attackers focus on Android, which is the most popular open-source operating system, as main target by applying some malicious software (malware) to access users' private information, control the device, or harm end-users. To detect Android malware, security experts have offered some learning-based models. In this study, we developed an Android malware detection system that uses different machine\deep learning models by performing both dynamic analyses, in which suspected malware is executed in a safe environment for observing its behaviours, and static analysis, which examines a malware file without any execution on the Android device. The benefits and weaknesses of these models and analyses are described in detail in this comparative study, and directions for future studies are drawn. Experimental results showed that the proposed models gave better results than those in the literature, with 0.988 accuracy for LSTM on static analysis and 0.953 accuracy for CNN-LSTM on dynamic analysis.https://hrcak.srce.hr/file/433793androiddeep learningmalware detection systemsmalware analysis |
| spellingShingle | Esra Calik Bayazit Ozgur Koray Sahingoz Buket Dogan Deep Learning based Malware Detection for Android Systems: A Comparative Analysis Tehnički Vjesnik android deep learning malware detection systems malware analysis |
| title | Deep Learning based Malware Detection for Android Systems: A Comparative Analysis |
| title_full | Deep Learning based Malware Detection for Android Systems: A Comparative Analysis |
| title_fullStr | Deep Learning based Malware Detection for Android Systems: A Comparative Analysis |
| title_full_unstemmed | Deep Learning based Malware Detection for Android Systems: A Comparative Analysis |
| title_short | Deep Learning based Malware Detection for Android Systems: A Comparative Analysis |
| title_sort | deep learning based malware detection for android systems a comparative analysis |
| topic | android deep learning malware detection systems malware analysis |
| url | https://hrcak.srce.hr/file/433793 |
| work_keys_str_mv | AT esracalikbayazit deeplearningbasedmalwaredetectionforandroidsystemsacomparativeanalysis AT ozgurkoraysahingoz deeplearningbasedmalwaredetectionforandroidsystemsacomparativeanalysis AT buketdogan deeplearningbasedmalwaredetectionforandroidsystemsacomparativeanalysis |