ADBuilder: a Datasets Building Tool for Android Malware Detection

• Lucas Vilanova UNIPAMPA http://orcid.org/0000-0002-7930-1097
• Diego Kreutz UNIPAMPA https://orcid.org/0000-0003-0830-0238
• Joner Assolin UFAM https://orcid.org/0000-0001-8517-6600
• Vagner Quincozes UNIPAMPA https://orcid.org/0000-0002-6688-5572
• Charles Miers UDESC https://orcid.org/0000-0002-1976-0478
• Rodrigo Mansilha UNIPAMPA https://orcid.org/0000-0002-2083-653X
• Eduardo Feitosa UFAM https://orcid.org/0000-0001-6401-3992

DOI: https://doi.org/10.5753/sbseg_estendido.2022.227038

Abstract

Most existing datasets have a limited number or lagged of samples, which compromises the training of models for Android malwares detection. In the literature there are some works that propose the construction of datasets, however, none of them sufficiently defined and integrated to the point of delivering a dataset in an automated and systematized way to the user. In this work, we propose the ADBuilder tool, which allows the integrated, automated and systematized construction of updated datasets for Android malwares detection domain. ADBuilder is made up of four independent modules, each module comprising a set of tools or services needed to build up-to-date datasets.

Keywords: Dataset Building Tool, Building Tool for Android Malware Detection, ADBuilder

References

Allix, K., Bissyandé, T. F., Klein, J., and Le Traon, Y. (2015). Are your training datasets yet relevant? In ESSoS, pages 51–67. Springer.

Catak, F. and Yazi, A. (2019). A benchmark api call dataset for windows pe malware classification. arXiv e-prints, pages arXiv–1905.

Düzgün, B., Cayr, A., Demirkran, F., Kayha, C. N., Gencaydn, B., and Dag, H. (2021). New datasets for dynamic malware classification. arXiv preprint arXiv:2111.15205.

Lashkari, A. H., Kadir, A. F. A., Taheri, L., and Ghorbani, A. A. (2018). Toward developing a systematic approach to generate benchmark android malware datasets and classification. In ICCST, pages 1–7. IEEE.

Mahindru, A. and Sangal, A. (2020). Somdroid: Android malware detection by artificial neural network trained using unsupervised learning. Evolutionary Intelligence.

Pan, Y., Ge, X., Fang, C., and Fan, Y. (2020). A systematic literature review of android malware detection using static analysis. IEEE Access, 8:116363–116379.

Pontes, J., Costa, E., Rocha, V., Neves, N., Feitosa, E., Assolin, J., and Kreutz, D. (2021). Ferramentas de extração de características para análise estática de aplicativos android. In WRSeg21.

Soares, T., Mello, J., Barcellos, L., Sayyed, R., Siqueira, G., Casola, K., Costa, E., Gustavo, N., Feitosa, E., and Kreutz, D. (2021a). Detecção de Malwares Android: Levantamento empírico da disponibilidade e da atualização das fontes de dados. In WRSeg21.

Soares, T., Siqueira, G., Barcellos, L., Sayyed, R., Vargas, L., Rodrigues, G., Assolin, J., Pontes, J., Feitosa, E., and Kreutz, D. (2021b). Detecção de Malwares Android: datasets e reprodutibilidade. In WRSeg21.

Wang, H., Si, J., Li, H., and Guo, Y. (2019). Rmvdroid: towards a reliable android malware dataset with app metadata. In IEEE/ACM 16th MSR, pages 404–408. IEEE.