An Intelligent ML-Based IDS Framework for DDoS Detection in the SDN Environment

Ameni Chetouane,Ghayth Nemri,Kamel Karoui

doi:10.1007/978-3-031-20436-4_2

Ameni Chetouane, Ghayth Nemri + Show 1 more

https://doi.org/10.1007/978-3-031-20436-4_2

Copy DOI

Export

Save

Cite

Abstract
Full-Text
Similar Papers

Abstract

Listen

AbstractSoftware Defined Networking (SDN) is a new approach that has the potential to revolutionize the way we run network infrastructure. In order to provide a network with attack countermeasures, an Intrusion Detection System (IDS) must be integrated into the SDN architecture. In this paper, we focus on IDS based on Machine Learning (ML) methods. The most problematic step in IDS evaluation is determining the appropriate dataset. Therefore, we propose a method that allows us to select the most appropriate dataset. In addition, the selection of an ML intrusion detection method related to an SDN architecture rather than another is another issue of this paper. We propose to integrate the severity of attacks into the standard metrics to differentiate between the quality of the results of ML methods. The severity of attacks will be computed using an adequate weighting of undetected intrusions (FN and FP) obtained in the testing phase. KeywordsSoftware Defined Networking (SDN)Network securitySecurity attacksDDoSIntrusion Detection System (IDS)Machine Learning (ML)

Full Text