Details
| DOI: | 10.1007/978-3-030-88113-9_19 |
|---|---|
| Publication type: | Conference paper |
| Conference: | ICCCI 2021: International Conference on Computer Communication and the Internet |
| Location: | Virtual |
| Online publication date: | 2021-09-27 |
Abstract
Handling the data imbalance problem is one of the crucial steps in a machine learning pipeline. The research community is well aware of the effects of data imbalance on machine learning algorithms. At the same time, there is a rising need for explainability of AI, especially in difficult, high-stake domains like network intrusion detection. In this paper, the effects of data balancing procedures on two explainability procedures implemented to explain a neural network used for network intrusion detection are evaluated. The discrepancies between the two methods are highlighted and important conclusions are drawn.
Authors
- Mateusz Szczepanski
ITTI Sp. z o.o. | UTP University of Science and Technology
Poznań, Poland | Bydgoszcz, Poland - Mikołaj Komisarek
This email address is being protected from spambots. You need JavaScript enabled to view it.
ITTI Sp. z o.o. | UTP University of Science and Technology
Poznań, Poland | Bydgoszcz, Poland - Marek Pawlicki
This email address is being protected from spambots. You need JavaScript enabled to view it.
ITTI Sp. z o.o. | UTP University of Science and Technology
Poznań, Poland | Bydgoszcz, Poland - Rafał Kozik
This email address is being protected from spambots. You need JavaScript enabled to view it.
ITTI Sp. z o.o. | UTP University of Science and Technology
Poznań, Poland | Bydgoszcz, Poland - Michał Choraś
This email address is being protected from spambots. You need JavaScript enabled to view it.
FernUniversität in Hagen | ITTI Sp. z o.o. | UTP University of Science and Technology
Hagen, Germany | Poznań, Poland | Bydgoszcz, Poland