A Study on the Introduction of CTGAN Oversampling Algorithm to improve Imbalance Problem in Intrusion Detection Data 


Vol. 45,  No. 12, pp. 2114-2122, Dec.  2020
10.7840/kics.2020.45.12.2114


PDF
  Abstract

Network intrusion detection data consists essentially of a large number of normal data and very few anomaly data. This data imbalance problem causes predictive performance degradation, such as misjudgment, with predicted bias and anomalies in a small number of data. Typical methods for solving the imbalance problem are various minority data synthesis models based on SMOTE algorithms. However, since the development of the Generative Adversarial Networks(GAN) model, research have been active on the synthesis of minority data using it. In this study, CTGAN oversampling model based on GAN Algorithm is used to solve the imbalance problem of intrusion detection data, and compare its performance with SMOTE-based models. In addition, generate attacks similar to those used in the experiment, extending the practical applicability of the classification model.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

Y. Choe and K. Oh, "A Study on the Introduction of CTGAN Oversampling Algorithm to improve Imbalance Problem in Intrusion Detection Data," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 12, pp. 2114-2122, 2020. DOI: 10.7840/kics.2020.45.12.2114.

[ACM Style]

Yoon-hee Choe and Kyoung-Whan Oh. 2020. A Study on the Introduction of CTGAN Oversampling Algorithm to improve Imbalance Problem in Intrusion Detection Data. The Journal of Korean Institute of Communications and Information Sciences, 45, 12, (2020), 2114-2122. DOI: 10.7840/kics.2020.45.12.2114.

[KICS Style]

Yoon-hee Choe and Kyoung-Whan Oh, "A Study on the Introduction of CTGAN Oversampling Algorithm to improve Imbalance Problem in Intrusion Detection Data," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 12, pp. 2114-2122, 12. 2020. (https://doi.org/10.7840/kics.2020.45.12.2114)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880