A Semi-Supervised Machine Learning Approach Using K-Means Algorithm to Prevent Burst Header Packet Flooding Attack in Optical Burst Switching Network

Abstract

Optical burst switching (OBS) network is a new generation optical communication technology. In an OBS network, an edge node first sends a control packet, called burst header packet (BHP) which reserves the necessary resources for the upcoming data burst (DB). Once the reservation is complete, the DB starts travelling to its destination through the reserved path. A notable attack on OBS network is BHP flooding attack where an edge node sends BHPs to reserve resources, but never actually sends the associated DB. As a result the reserved resources are wasted and when this happen in sufficiently large scale, a denial of service (DoS) may take place. In this study, we propose a semi-supervised machine learning approach using k-means algorithm, to detect malicious nodes in an OBS network. The proposed semi-supervised model was trained and validated with small amount data from a selected dataset. Experiments show that the model can classify the nodes into either behaving or not-behaving classes with 90% accuracy when trained with just 20% of data. When the nodes are classified into behaving, not-behaving and potentially not-behaving classes, the model shows 65.15% and 71.84% accuracy if trained with 20% and 30% of data respectively. Comparison with some notable works revealed that the proposed model outperforms them in many respects.