Cloud AutoDroid: A Backend Architecture for Running Generative AI Services in the Cloud

• Luiz Felipe Laviola UNIPAMPA http://orcid.org/0009-0004-0055-0691
• Angelo Gaspar Diniz Nogueira UNIPAMPA http://orcid.org/0009-0002-7765-3475
• Diego Kreutz UNIPAMPA http://orcid.org/0000-0003-0830-0238
• Rodrigo Brandão Mansilha UNIPAMPA http://orcid.org/0000-0002-2083-653X

DOI: https://doi.org/10.5753/eres.2024.4302

Abstract

We present Cloud AutoDroid: a distributed software architecture, based on lightweight virtualization, that provides Artificial Intelligence (AI) tools as a service in a simplified and horizontally scalable manner. The architecture is flexible, allowing the execution and monitoring of both current and future AI services and infrastructures. We demonstrate the technical feasibility of the proposal through an implementation of Cloud AutoDroid and a set of functional tests. Additionally, we assess the applicability of Cloud AutoDroid through a case study within the Malware DataLab project, supported by the Brazilian National Education and Research Network (RNP).

Keywords: software engineering, cloud computing, software architecture, distributed computing, virtualization

References

AI & Data Today (2023). Top 10 reasons why ai projects fail. [link].

Casola, K., Paim, K., Mansilha, R., and Kreutz, D. (2023). DroidAugmentor: uma ferramenta de treinamento e avaliação de cGANs para geração de dados sintéticos.

Hong, Y. S., No, J., and Kim, S. (2006). DNS-based load balancing in distributed web-server systems. In The Fourth IEEE Workshop on Software Technologies for Future Embedded and Ubiquitous Systems, and the Second International Workshop on Collaborative Computing, Integration, and Assurance (SEUS-WCCIA’06), pages 4–pp. IEEE.

Jones, M. (2015). Json web token (jwt). Internet Engineering Task Force (IETF) RFC, 7519.

Kouliaridis, V., Kambourakis, G., and Peng, T. (2020). Feature importance in android malware detection. In 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), pages 1449–1454. IEEE.

Laviola, L., Paim, K., Kreutz, D., and Mansilha, R. (2023). AutoDroid: disponibilizando a ferramenta DroidAugmentor como serviço. In Anais da XX Escola Regional de Redes de Computadores, pages 145–150, Porto Alegre, RS, Brasil. SBC.

Meijin, L., Zhiyang, F., Junfeng, W., Luyu, C., Qi, Z., Tao, Y., Yinwei, W., and Jiaxuan, G. (2022). A systematic overview of android malware detection. Applied Artificial Intelligence, 36(1):2007327.

Miranda, T. C., Gimenez, P.-F., Lalande, J.-F., Tong, V. V. T., and Wilke, P. (2022). Debiasing android malware datasets: How can i trust your results if your dataset is biased? IEEE Transactions on Information Forensics and Security, 17:2182–2197.

Nogueira, A., Paim, K., Bragança, H., Mansilha, R., and Kreutz, D. (2024a). Geração de dados sintéticos tabulares para detecção de malware android: um estudo de caso. In Anais do XXIV Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais, pages 808–814, Porto Alegre, RS, Brasil. SBC.

Nogueira, A., Paim, K., Bragança, H., Mansilha, R., and Kreutz, D. (2024b). Malsyngen: redes neurais artificiais na geração de dados tabulares sintéticos para detecção de malware. In Anais Estendidos do XXIV Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais, pages 129–136, Porto Alegre, RS, Brasil. SBC.

Wang, H., Si, J., Li, H., and Guo, Y. (2019). RmvDroid: Towards a reliable android malware dataset with app metadata. In 2019 IEEE/ACM 16th International Conference on Mining Software Repositories (MSR), pages 404–408.