Microsserviços para Geração de RCLs no GRASP-FS: Uma Abordagem Escalável para Seleção de Features na Detecção de Intrusões em Sistemas Ciber-Físicos

• Nícolas Naves R. Faria UFU
• Silvio E. Quincozes UFU / UNIPAMPA
• Juliano F. Kazienko UFSM
• Vagner E. Quincozes UFF
• Gabriel Oliveira UFU
• Estevão F. C. Silva UFU

DOI: https://doi.org/10.5753/sbseg.2023.232948

Abstract

This paper presents a scalable microservices-oriented architecture, called Distributed RCL Generator (DRG), to decouple and parallelize the construction phase in the Greedy Randomized Adaptive Search Procedure for Feature Selection (GRASP-FS) metaheuristic in Feature Selection (FS) for intrusion detection. In GRASP-FS, the construction phase generates initial feature subsets that are optimized in the local search phase. As a proof-of-concept based on the Kafka framework and four FS algorithms, we demonstrated that the adopted algorithm strategy impacts the intrusion detection F1-Score in a Cyber-Physical Systems scenario ranging from 50.47% to 84.92%. Finally, we show that parallel processing can accelerate the construction phase about 3.4 times.

References

Ajeet Singh Raina and Johan Giraldo (2022). Kickstart Your Spring Boot Application Development. Disponível em: [link]. Acesso em: 18 de Novembro 2022.

Anderson, C. (2015). Docker [software engineering]. IEEE Software, 32(3):102–c3.

Carvalho, D., Quincozes, V. E., Quincozes, S. E., Kazienko, J. F., and dos Santos, C. R. P. (2022). BGIDPS: Detecção e Prevenção de Intrusões em Tempo Real em Switches eBPF com o Filtro de Pacotes Berkeley e a Metaheurística GRASP-FS. In XXII Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais, pages 139–152. SBC.

Diez-Pastor, J.-F., Garcia-Osorio, C., and Rodriguez, J. J. (2014). Tree ensemble construction using a GRASP-based heuristic and annealed randomness. Information Fusion, 20:189–202.

Diez-Pastor, J. F., Garcıa-Osorio, C., Rodrıguez, J. J., and Bustillo, A. (2011). GRASP Forest: A New Ensemble Method for Trees. In International Workshop on Multiple Classifier Systems, pages 66–75.

Esseghir, M. A. (2010). Effective wrapper-filter hybridization through grasp schemata. In Feature selection in data mining, pages 45–54. PMLR.

FortiGuard Labs (2021). Brasil sofreu mais de 88,5 bilhões de tentativas de ataques cibernéticos em 2021. Disponível em: [link]. Acesso em: 15 de Março de 2023.

Garg, N. (2013). Apache Kafka. Packt Publishing Birmingham, UK.

Kanakarajan, N. K. and Muniasamy, K. (2016). Improving the accuracy of intrusion detection using garforest with feature selection. In Proceedings of the 4th International Conference on Frontiers in Intelligent Computing: Theory and Applications (FICTA) 2015, pages 539–547. Springer.

Kira, K. and Rendell, L. A. (1992). A practical approach to feature selection. In Machine learning proceedings 1992, pages 249–256. Elsevier.

Kononenko, I. et al. (1994). Estimating attributes: Analysis and extensions of relief. In ECML, volume 94, pages 171–182. Citeseer.

Newman, S. (2021). Building microservices. ”O’Reilly Media, Inc.”.

Quincozes, S. E., Albuquerque, C., Passos, D., and Mossé, D. (2021a). A survey on intrusion detection and prevention systems in digital substations. Computer Networks, 184:107679.

Quincozes, S. E., Albuquerque, C., Passos, D., and Mossé, D. (2022a). ERENO: An Extensible Tool For Generating Realistic IEC-61850 Intrusion Detection Datasets. In Concurso de Teses e Dissertações do XXII Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais, pages 1–8.

Quincozes, S. E., Mossé, D., Passos, D., Albuquerque, C., Ochi, L. S., and dos Santos, V. F. (2021b). On the Performance of GRASP-Based Feature Selection for CPS Intrusion Detection. IEEE Transactions on Network and Service Management, 19(1):614–626.

Quincozes, S. E., Passos, D., Albuquerque, C., Mossé, D., and Ochi, L. S. (2022b). An extended assessment of metaheuristics-based feature selection for intrusion detection in CPS perception layer. Annals of Telecommunications, pages 1–15.

Quincozes, S. E., Passos, D., Albuquerque, C., Ochi, L. S., and Mossé, D. (2020). GRASP-based Feature Selection for Intrusion Detection in CPS Perception Layer. In 2020 4th Conference on Cloud and Internet of Things (CIoT), pages 41–48. IEEE.

Quinlan, J. R. (1986). Induction of decision trees. Machine learning, 1:81–106.

Quinlan, J. R. (1993). Program for machine learning. C4. 5.

Rocha, H. P., Ladeira, R. W. S., and Braga, A. P. (2015). Análise de Métodos Construtivos, Busca Local e Metaheurísticas para o Problema de Seleção de Características. In Anais do XII Congresso Brasileiro de Inteligência Computacional, pages 1–6.

Silva, E. F. C., Naves, N., Quincozes, S. E., Quincozes, V. E., Kazienko, J. F., and Cheikhrouhou, O. (2023). GDLS-FS: Scaling Feature Selection for Intrusion Detection with GRASP-FS and Distributed Local Search. In 37th Int. Conf. on Advanced Information Networking and Applications, pages 199–210.

Witten, I. H., Frank, E., and Hall, M. A. (2011). Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, Amsterdam, 3 edition.

You, L. and Sun, H. (2022). Research and design of docker technology based authority management system. Computational Intelligence and Neuroscience, 2022.