An Efficient Hybrid Model For Scalable Distributed Denial-of-Service Detection in Software Defined Network

Srinivasan, Devanand (2025) An Efficient Hybrid Model For Scalable Distributed Denial-of-Service Detection in Software Defined Network. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Distributed Denial-of-Service attack detection in Software-Defined Networks is essential on a network-wide level to minimise service interruption and mitigate the number of victims. Current sketch-based detection techniques can be characterized as glued to the assumption of stable routing behaviour that may not hold under dynamic traffic conditions. This project involves a routing-oblivious sketching-based flow-based Distributed Denial-of-Service detection framework, based on a hybrid data-plane and control-plane architecture. In the proposed system, programmable switches perform lightweight data-plane monitoring using a Lemon-style sketch to aggregate per-destination traffic statistics over fixed time windows without keeping per-flow state. Periodically these sketches are combined in the control plane to get network-wide flow estimates. Flow-level features are also extracted and analysed with an adaptive Concept-Adapting Very Fast Decision Tree (algorithm) machine learning model to determine whether the traffic is benign or malicious when abnormal traffic behaviour is observed. The framework is deployed to a software switch-based Software-Defined Networks emulation environment and tested with benign and attack traffic based on the Canadian Institute for Cybersecurity dataset. Findings indicate that the hybrid flow-based detection is indeed effective in Software-Defined Networks concerning both proper detection and low false alarm rates with minimal control-plane overhead.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hamdan, Mosab UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	04 Sep 2026 11:13
Last Modified:	04 Sep 2026 11:13
URI:	https://norma.ncirl.ie/id/eprint/9836

Actions (login required)

View Item