Stacking-based Committees para Detecção de Ataques em Redes de Computadores - Uma abordagem por exaustão

• Thiago J. Lucas UNESP
• Kelton A. P. da Costa UNESP
• Eduardo A. Moraes FATEC
• Paulo R. G. Hernandes Júnior FATEC
• Miguel J. das Neves FATEC

DOI: https://doi.org/10.5753/sbrc.2021.16753

Abstract

The application of Machine Learning techniques in detecting attacks on computer networks has obtained good results, emphasizing the methods of Ensemble, which manage to improve the performance of individual classifiers. The present study was carried out in Dataset CICIDS-2017 and considered classifiers' choice based on a systematic review of the literature, aiming to find the state-of-the-art and trends, both for the classification algorithms and the ensemble techniques. Committees that significantly reduce classification errors are presented by modeling intrusion detectors that are superior to individual methods and related work compared with an average accuracy of 99.92%.

References

Agarwal, S. and Chowdary, C. R. (2020). A-stacking and a-bagging: Adaptive versions of ensemble learning algorithms for spoof fingerprint detection. Expert Systems with Applications, 146:113160.

Aggarwal, C. (2014). Data classification: Algorithms and applications, ser. Frontiers in physics. Chapman and Hall/CRC.

Baeza-Yates, R. and Ribeiro-Neto, B. (2013). Recuperação de Informação-: Conceitos e Tecnologia das Máquinas de Busca. Bookman Editora.

Belouch, M. and hadaj, S. E. (2017). Comparison of ensemble learning methods applied to network intrusion detection. In Proceedings of the Second International Conference on Internet of things, Data and Cloud Computing, pages 1–4.

Deng, Z., Zhu, X., Cheng, D., Zong, M., and Zhang, S. (2016). Efficient knn classification algorithm for big data. Neurocomputing, 195:143–148.

Dzeroski, S. and Zenko, B. (2004). Is combining classifiers with stacking better than selecting the best one? Machine learning, 54(3):255–273.

Fraimovich, D. Y., Donichev, O. A., Grachev, S. A., and Gundorova, M. A. (2020). The In Growth Poles role of information and digital resources in regional development. of the Global Economy: Emergence, Changes and Future Perspectives, pages 1305– 1316. Springer.

Hsu, Y.-F., He, Z., Tarutani, Y., and Matsuoka, M. (2019). Toward an online network intrusion detection system based on ensemble learning. In 2019 IEEE 12th International Conference on Cloud Computing (CLOUD), pages 174–178. IEEE.

Karatas, G. and Sahingoz, O. K. (2018). Neural network based intrusion detection systems In 2018 6th International Symposium on Digital with different training functions. Forensic and Security (ISDFS), pages 1–6. IEEE.

Lu, L., Teng, S., Zhang, W., Zhang, Z., Liu, D., and Fang, X. (2019). Error-correcting ability based collaborative multi-layer selective classifier ensemble model for intrusion detection. In 2019 IEEE 23rd International Conference on Computer Supported Cooperative Work in Design (CSCWD), pages 4–9. IEEE.

Milliken, M., Bi, Y., Galway, L., and Hawe, G. (2015). Ensemble learning utilising feature pairings for intrusion detection. In 2015 World Congress on Internet Security (WorldCIS), pages 24–31. IEEE.

Olasehinde, O. O., Johnson, O. V., and Olayemi, O. C. (2020). Evaluation of selected meta learning algorithms for the prediction improvement of network intrusion detection system. In 2020 International Conference in Mathematics, Computer Engineering and Computer Science (ICMCECS), pages 1–7. IEEE.

Panigrahi, R. and Borah, S. (2018). A detailed analysis of cicids2017 dataset for designing intrusion detection systems. International Journal of Engineering & Technology, 7(3.24):479–482.

Rezende, S. O. (2003). Sistemas inteligentes: fundamentos e aplicações. Editora Manole Ltda.

Rocca, J. (2019). Ensemble methods: bagging, boosting and stacking - towards data science. [link]. (Accesso en 23/04/2020).

Sharaf., I., Lashkari, A., Habibi, and Ghorbani, A. A. (2018). Toward generating a new intrusion detection dataset and intrusion traffic characterization. In ICISSP, pages 108–116.

Sharma, H. and Kumar, S. (2016). A survey on decision tree algorithms of classification in data mining. International Journal of Science and Research (IJSR), 5(4):2094–2097.

Smolyakov, V. (2017). Ensemble learning to improve machine learning results. https://blog.statsbot.co/ensemble-learning-d1dcd548e936. (Acesso em 30/09/2019).

Stiawan, D., Idris, M. Y. B., Bamhdi, A. M., Budiarto, R., et al. (2020). Cicids-2017 dataset feature analysis with information gain for anomaly detection. IEEE Access, 8:132911–132921.

Sun, C., Lv, K., Hu, C., and Xie, H. (2018). A double-layer detection and classification approach for network attacks. In 2018 27th International Conference on Computer Communication and Networks (ICCCN), pages 1–8. IEEE.

Tama, B. A., Nkenyereye, L., Islam, S. R., and Kwak, K.-S. (2020). An enhanced anomaly detection in web traffic using a stack of classifier ensemble. IEEE Access, 8:24120– 24134.

Tchaye-Kondi, J., Zhai, Y., and Zhu, L. (2020). A new hashing based nearest neighbors selection technique for big datasets. arXiv preprint arXiv:2004.02290.

Tinós, R. (2020). Perceptron multicamadas. [link]. (Acesso em 04/15/2020).

Wolpert, D. H. (1992). Stacked generalization. Neural networks, 5(2):241–259. Zhou, Z.-H. (2012). Ensemble methods: foundations and algorithms. Chapman and Hall/CRC.