TY - GEN
T1 - Bytecode-Based Android Malware Detection Applying Convolutional Neural Networks
AU - Miranda-Garcia, Alberto
AU - Pastor-López, Iker
AU - Urquijo, Borja Sanz
AU - de la Puerta, José Gaviria
AU - Bringas, Pablo García
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Over the past decade, mobile devices have become an integral part of our daily lives. These devices rely on applications to deliver a diverse range of services and functionalities to users, such as social networks or online shopping apps. The usage of these applications has led to the emergence of novel security risks, facilitating the rapid proliferation of malicious apps. To deal with the increasing numbers of Android malware in the wild, deep learning models have emerged as promising detection systems. In this paper, we propose an Android malware detection system using Convolutional Neural Networks (CNN). To accomplish this objective, we trained three distinct models (VGG16, RESNET50, and InceptionV3) on the image representation of the Dalvik executable format. Our assessment, conducted on a dataset of more than 13000 samples, showed that all three models performed up to 99% of the detection of malicious Android applications. Finally, we discuss the potential benefits of employing this type of solution for detecting Android malware.
AB - Over the past decade, mobile devices have become an integral part of our daily lives. These devices rely on applications to deliver a diverse range of services and functionalities to users, such as social networks or online shopping apps. The usage of these applications has led to the emergence of novel security risks, facilitating the rapid proliferation of malicious apps. To deal with the increasing numbers of Android malware in the wild, deep learning models have emerged as promising detection systems. In this paper, we propose an Android malware detection system using Convolutional Neural Networks (CNN). To accomplish this objective, we trained three distinct models (VGG16, RESNET50, and InceptionV3) on the image representation of the Dalvik executable format. Our assessment, conducted on a dataset of more than 13000 samples, showed that all three models performed up to 99% of the detection of malicious Android applications. Finally, we discuss the potential benefits of employing this type of solution for detecting Android malware.
KW - Android
KW - Bytecodes
KW - CNN
KW - Deep learning
KW - Malware detection
UR - https://www.scopus.com/pages/publications/85171445085
U2 - 10.1007/978-3-031-42519-6_11
DO - 10.1007/978-3-031-42519-6_11
M3 - Conference contribution
AN - SCOPUS:85171445085
SN - 9783031425189
T3 - Lecture Notes in Networks and Systems
SP - 111
EP - 121
BT - International Joint Conference 16th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2023) 14th International Conference on EUropean Transnational Education (ICEUTE 2023) - Proceedings
A2 - García Bringas, Pablo
A2 - Pérez García, Hilde
A2 - Martínez de Pisón, Francisco Javier
A2 - Martínez Álvarez, Francisco
A2 - Troncoso Lora, Alicia
A2 - Herrero, Álvaro
A2 - Calvo Rolle, José Luis
A2 - Quintián, Héctor
A2 - Corchado, Emilio
PB - Springer Science and Business Media Deutschland GmbH
T2 - 16th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2023 and 14th International Conference on EUropean Transnational Education, ICEUTE 2023
Y2 - 5 September 2023 through 7 September 2023
ER -