A new android malware detection method based on multimodal deep learning and hybrid analysis

• Ano de defesa: 2022
• Autor(a) principal: Oliveira, Angelo Schranko de
• Orientador(a): Sassi, Renato José
• Banca de defesa: Sassi, Renato José , Lopes, Fábio Silva , Silva, Leandro Augusto da , Dias, Cleber Gustavo , Martins, Fellipe Silva
• Tipo de documento: Tese
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Universidade Nove de Julho
• Programa de Pós-Graduação: Programa de Pós-Graduação em Informática e Gestão do Conhecimento
• Departamento: Informática
• País: Brasil
• Palavras-chave em Português: android malware detection; multimodal deep learning; computer security
• Palavras-chave em Inglês: android malware detection; multimodal deep learning; computer security
• Área do conhecimento CNPq: CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO
• Link de acesso: http://bibliotecatede.uninove.br/handle/tede/3096

In the current world, whereby almost everything is digitized, cybercrime is on the rise as criminals continue to develop new ways to hack information systems. One of main tools used for cybercrime operations are malware, or malicious software. Malware detection is a challenging problem that has been actively explored by both the industry and academia using intelligent methods. On the one hand, traditional Machine Learning (ML) malware detection methods rely on manual feature engineering that requires expert knowledge. On the other hand, Deep Learning (DL) malware detection methods perform automatic feature learning but usually require much more data and processing power. Moreover, there are multiple data modalities of Malware Analysis (MA) data that can be used for detection purposes. Thus, the general objective of this dissertation was to develop and evaluate a new Android malware detection method, named Chimera, based on Multimodal Deep Learning (MDL) and Hybrid Analysis (HA), using different data modalities and combining both manual and automatic feature engineering in order to increase Android malware detection rate. To train, optimize, and evaluate the models, the Knowledge Discovery in Databases (KDD) process was implemented using a new dataset based on the publicly available Android benchmark dataset Omnidroid containing Static Analysis (SA) and Dynamic Analysis (DA) data extracted from 22000 real malware and goodware samples. By leveraging a hybrid source of information to learn high-level feature representations for both the static and dynamic properties of Android applications, Chimera’s performance outperformed its unimodal DL subnetworks, classical ML methods, and Ensemble ML methods, thus, the results of this dissertation show that the right combination of multimodal data, specialized DL methods, manual and automatic feature engineering can significantly increase Android malware detection rate.