Android Malware Analysis and Benchmarking with Deep Learning
Android operating system has been widely used in mobile phones, televisions, smart watches, cars and other Internet of Things applications with its open source structure and wide application market. This widespread use and open-source nature make this operating system and its devices easy and lucrat...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Düzce University
2021-12-01
|
| Series: | Düzce Üniversitesi Bilim ve Teknoloji Dergisi |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/tr/download/article-file/2050247 |
| _version_ | 1826544690530353152 |
|---|---|
| author | Murat Dener Yusuf Sönmez Taylan Kural |
| author_facet | Murat Dener Yusuf Sönmez Taylan Kural |
| author_sort | Murat Dener |
| collection | DOAJ |
| description | Android operating system has been widely used in mobile phones, televisions, smart watches, cars and other Internet of Things applications with its open source structure and wide application market. This widespread use and open-source nature make this operating system and its devices easy and lucrative targets for cyber attackers. One of the most used methods often preferred by attackers is to install malware applications on user devices. As the number of malware programs is increasing, the traditional methods can be insufficient in detecting. Machine learning-based and deep learning-based methods have achieved promising results in malware detection and classification. Deep learning-based methods have an increasing use in malware detection, thanks to the low need for domain expertise and their feature extracting capabilities. Convolutional neural networks (CNN) are popular deep learning methods that are widely used in visual analysis of malware by transforming them to images. In this study, a batch fine-tune transfer learning method was proposed and used on popular CNN models, Xception, ResNet, VGG, Inception, MobileNet, DenseNet, NasNet, EfficientNet. According to the results, the models were analyzed and compared with metrics like accuracy, specificity, recall, precision, F1-score. |
| first_indexed | 2024-03-07T23:13:05Z |
| format | Article |
| id | doaj.art-8deb05212e354646a19dcca1d19a4a50 |
| institution | Directory Open Access Journal |
| issn | 2148-2446 |
| language | English |
| last_indexed | 2025-03-14T05:05:59Z |
| publishDate | 2021-12-01 |
| publisher | Düzce University |
| record_format | Article |
| series | Düzce Üniversitesi Bilim ve Teknoloji Dergisi |
| spelling | doaj.art-8deb05212e354646a19dcca1d19a4a502025-03-06T18:57:31ZengDüzce UniversityDüzce Üniversitesi Bilim ve Teknoloji Dergisi2148-24462021-12-019628930210.29130/dubited.101565497Android Malware Analysis and Benchmarking with Deep LearningMurat Dener0https://orcid.org/0000-0001-5746-6141Yusuf Sönmez1https://orcid.org/0000-0002-9775-9835Taylan Kural2https://orcid.org/0000-0002-8316-4654GAZİ ÜNİVERSİTESİ, FEN BİLİMLERİ ENSTİTÜSÜ, BİLGİ GÜVENLİĞİ MÜHENDİSLİĞİ ANABİLİM DALI (DİSİPLİNLERARASI)Faculty of Information and Telecommunication Technologies, Azerbaijan Technical UniversityGAZİ ÜNİVERSİTESİ, FEN BİLİMLERİ ENSTİTÜSÜ, BİLGİ GÜVENLİĞİ MÜHENDİSLİĞİ ANABİLİM DALI (DİSİPLİNLERARASI), BİLGİ GÜVENLİĞİ MÜHENDİSLİĞİ (YL) (TEZLİ)Android operating system has been widely used in mobile phones, televisions, smart watches, cars and other Internet of Things applications with its open source structure and wide application market. This widespread use and open-source nature make this operating system and its devices easy and lucrative targets for cyber attackers. One of the most used methods often preferred by attackers is to install malware applications on user devices. As the number of malware programs is increasing, the traditional methods can be insufficient in detecting. Machine learning-based and deep learning-based methods have achieved promising results in malware detection and classification. Deep learning-based methods have an increasing use in malware detection, thanks to the low need for domain expertise and their feature extracting capabilities. Convolutional neural networks (CNN) are popular deep learning methods that are widely used in visual analysis of malware by transforming them to images. In this study, a batch fine-tune transfer learning method was proposed and used on popular CNN models, Xception, ResNet, VGG, Inception, MobileNet, DenseNet, NasNet, EfficientNet. According to the results, the models were analyzed and compared with metrics like accuracy, specificity, recall, precision, F1-score.https://dergipark.org.tr/tr/download/article-file/2050247deep learningandroid malware analysisimage analysisderin öğrenmeandroid kötücül yazılım analizigörsel analiz |
| spellingShingle | Murat Dener Yusuf Sönmez Taylan Kural Android Malware Analysis and Benchmarking with Deep Learning Düzce Üniversitesi Bilim ve Teknoloji Dergisi deep learning android malware analysis image analysis derin öğrenme android kötücül yazılım analizi görsel analiz |
| title | Android Malware Analysis and Benchmarking with Deep Learning |
| title_full | Android Malware Analysis and Benchmarking with Deep Learning |
| title_fullStr | Android Malware Analysis and Benchmarking with Deep Learning |
| title_full_unstemmed | Android Malware Analysis and Benchmarking with Deep Learning |
| title_short | Android Malware Analysis and Benchmarking with Deep Learning |
| title_sort | android malware analysis and benchmarking with deep learning |
| topic | deep learning android malware analysis image analysis derin öğrenme android kötücül yazılım analizi görsel analiz |
| url | https://dergipark.org.tr/tr/download/article-file/2050247 |
| work_keys_str_mv | AT muratdener androidmalwareanalysisandbenchmarkingwithdeeplearning AT yusufsonmez androidmalwareanalysisandbenchmarkingwithdeeplearning AT taylankural androidmalwareanalysisandbenchmarkingwithdeeplearning |