Problemas e alternativas ao uso da base KDDCUP’99, para classificação de ataques em redes IP
Resumo
O presente documento busca abordar as limitações da base KDDCUP’99, sugerindo como alternativa de uso da base UNSW-NB15. Para verificar o principal problema da base KDD, a facilidade de classificação dos dados, são utilizados três métodos de classificação: florestas aleatórias, SVM e redes neurais.Referências
Adhikary, K., Bhushan, S., Kumar, S., e Dutta, K. (2021). Evaluating the performance of various svm kernel functions based on basic features extracted from kddcup’99 dataset by random forest method for detecting ddos attacks. Wireless Personal Communications, 123(4):3127–3145.
Meliboev, A., Alikhanov, J., e Kim, W. (2022). Performance evaluation of deep learning based network intrusion detection system across multiple balanced and imbalanced datasets. Electronics, 11(4):515.
Moustafa, N. e Slay, J. (2015). Unsw-nb15: a comprehensive data set for network intrusion detection systems (unsw-nb15 network data set). Em 2015 Military Communications and Information Systems Conference (MilCIS), páginas 1–6. IEEE.
Moustafa, N. e Slay, J. (2016). The evaluation of network anomaly detection systems: Statistical analysis of the unsw-nb15 data set and the comparison with the kdd99 data set. Information Security Journal: A Global Perspective, 25(1–3):18–31.
Sapre, S., Ahmadi, P., e Islam, K. (2019). A robust comparison of the kddcup99 and nsl-kdd iot network intrusion detection datasets through various machine learning algorithms.
Tavallaee, M., Bagheri, E., Lu, W., e Ghorbani, A. A. (2009). A detailed analysis of the kdd cup 99 data set. Em 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, páginas 1–6. IEEE.
Meliboev, A., Alikhanov, J., e Kim, W. (2022). Performance evaluation of deep learning based network intrusion detection system across multiple balanced and imbalanced datasets. Electronics, 11(4):515.
Moustafa, N. e Slay, J. (2015). Unsw-nb15: a comprehensive data set for network intrusion detection systems (unsw-nb15 network data set). Em 2015 Military Communications and Information Systems Conference (MilCIS), páginas 1–6. IEEE.
Moustafa, N. e Slay, J. (2016). The evaluation of network anomaly detection systems: Statistical analysis of the unsw-nb15 data set and the comparison with the kdd99 data set. Information Security Journal: A Global Perspective, 25(1–3):18–31.
Sapre, S., Ahmadi, P., e Islam, K. (2019). A robust comparison of the kddcup99 and nsl-kdd iot network intrusion detection datasets through various machine learning algorithms.
Tavallaee, M., Bagheri, E., Lu, W., e Ghorbani, A. A. (2009). A detailed analysis of the kdd cup 99 data set. Em 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, páginas 1–6. IEEE.
Publicado
12/11/2025
Como Citar
BALBINOT, Ricardo; BALBINOT, Alexandre; MÜLLER, Ivan.
Problemas e alternativas ao uso da base KDDCUP’99, para classificação de ataques em redes IP. In: ESCOLA REGIONAL DE APRENDIZADO DE MÁQUINA E INTELIGÊNCIA ARTIFICIAL DA REGIÃO SUL (ERAMIA-RS), 1. , 2025, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 29-32.
DOI: https://doi.org/10.5753/eramiars.2025.16476.
