MH-AutoML: Transparência, Interpretabilidade e Desempenho na Detecção de Malware Android
Resumo
A MH-AutoML é uma ferramenta de AutoML especializada na detecção de malware Android. Diferentemente de outras ferramentas de AutoML, a MH-AutoML incorpora recursos de transparência, interpretabilidade e depuração em todos os estágios do pipeline. A ferramenta também inclui métodos de seleção de caracteŕısticas espećıficos para o domínio e otimizações de hiperparâmetros que geram bons resultados. Os resultados indicam que a MH-AutoML produz modelos preditivos competitivos (e.g., 95% de recall com baixo custo computacional) em comparação com modelos gerados por outras 7 ferramentas de AutoML.Referências
Assolin, J. et. al. (2024). MH-AutoML. [link].
Erickson, N. et. al. (2020). Autogluon-tabular: Robust and accurate automl for structured data. arXiv preprint arXiv:2003.06505.
Guyon, I. et. al. (2015). Design of the 2015 chalearn automl challenge. In International Joint Conference on Neural Networks (IJCNN), pages 1–8.
Jin, H., Chollet, F., Song, Q., and Hu, X. (2023). Autokeras: An automl library for deep learning. Journal of machine Learning research, 24(6):1–6.
Karmaker S. et. al. (2021). Automl to date and beyond: Challenges and opportunities. ACM Computing Surveys, 54(8).
LeDell, E. and Poirier, S. (2020). H2o automl: Scalable automatic machine learning. In Proceedings of the AutoML Workshop at ICML, volume 2020.
Lee, D. J.-L. and Macke, S. (2020). A human-in-the-loop perspective on automl: Milestones and the road ahead. IEEE Data Engineering Bulletin.
Molino P. et. al. (2019). Ludwig: a type-based declarative deep learning toolbox.
Nasimian, A. et. al. (2024). Alphaml: A clear, legible, explainable, transparent, and elucidative binary classification platform for tabular data. Patterns, 5(1).
Olson, R. S. and Moore, J. H. (2016). TPOT: A tree-based pipeline optimization tool for automating machine learning. In Workshop on automatic machine learning.
Shi, X. et. al. (2021). An automated machine learning (automl) method of risk prediction for decision-making of autonomous vehicles. IEEE TITS, 22(11):7145.
Xin, D. et. al. (2021). Whither automl? understanding the role of automation in machine learning workflows. In Proceedings of the CHI.
Yan, C. et. al. (2022). Privacy-preserving online automl for domain-specific face detection. In IEEE CVF, pages 4134–4144.
Zimmer, L., Lindauer, M., and Hutter, F. (2000). Auto-pytorch tabular: Multi-fidelity metalearning for efficient and robust autodll. arxiv 2020. arXiv preprint arXiv:2006.13799.
Erickson, N. et. al. (2020). Autogluon-tabular: Robust and accurate automl for structured data. arXiv preprint arXiv:2003.06505.
Guyon, I. et. al. (2015). Design of the 2015 chalearn automl challenge. In International Joint Conference on Neural Networks (IJCNN), pages 1–8.
Jin, H., Chollet, F., Song, Q., and Hu, X. (2023). Autokeras: An automl library for deep learning. Journal of machine Learning research, 24(6):1–6.
Karmaker S. et. al. (2021). Automl to date and beyond: Challenges and opportunities. ACM Computing Surveys, 54(8).
LeDell, E. and Poirier, S. (2020). H2o automl: Scalable automatic machine learning. In Proceedings of the AutoML Workshop at ICML, volume 2020.
Lee, D. J.-L. and Macke, S. (2020). A human-in-the-loop perspective on automl: Milestones and the road ahead. IEEE Data Engineering Bulletin.
Molino P. et. al. (2019). Ludwig: a type-based declarative deep learning toolbox.
Nasimian, A. et. al. (2024). Alphaml: A clear, legible, explainable, transparent, and elucidative binary classification platform for tabular data. Patterns, 5(1).
Olson, R. S. and Moore, J. H. (2016). TPOT: A tree-based pipeline optimization tool for automating machine learning. In Workshop on automatic machine learning.
Shi, X. et. al. (2021). An automated machine learning (automl) method of risk prediction for decision-making of autonomous vehicles. IEEE TITS, 22(11):7145.
Xin, D. et. al. (2021). Whither automl? understanding the role of automation in machine learning workflows. In Proceedings of the CHI.
Yan, C. et. al. (2022). Privacy-preserving online automl for domain-specific face detection. In IEEE CVF, pages 4134–4144.
Zimmer, L., Lindauer, M., and Hutter, F. (2000). Auto-pytorch tabular: Multi-fidelity metalearning for efficient and robust autodll. arxiv 2020. arXiv preprint arXiv:2006.13799.
Publicado
16/09/2024
Como Citar
ASSOLIN, Joner; CANTO, Gabriel; KREUTZ, Diego; FEITOSA, Eduardo.
MH-AutoML: Transparência, Interpretabilidade e Desempenho na Detecção de Malware Android. In: SALÃO DE FERRAMENTAS - SIMPÓSIO BRASILEIRO DE SEGURANÇA DA INFORMAÇÃO E DE SISTEMAS COMPUTACIONAIS (SBSEG), 24. , 2024, São José dos Campos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 113-120.
DOI: https://doi.org/10.5753/sbseg_estendido.2024.243362.
