Researchers have developed a new artificial intelligence-based system designed to improve cyberattack detection in software-defined networks (SDNs), a networking architecture widely used in data centres and enterprise systems.
The system combines a deep quantum neural network with a novel optimisation technique inspired by the behaviour of wild geese and dwarf mongooses. Its aim is to identify abnormal network traffic, including distributed denial-of-service (dDoS) attacks, while preventing network controllers from becoming overloaded.
SDNs differ from traditional networks by separating the control plane, which makes routing decisions, from the data plane, which forwards traffic. While this design improves flexibility and centralises management, it also creates potential targets for attackers seeking to disrupt communications between controllers and network devices.
In the new approach outlined in the International Journal of Heavy Vehicle Systems, network traffic is analysed using a deep quantum neural network, a machine-learning model designed to recognise complex patterns. When suspicious traffic is detected, the system assesses controller workloads and automatically transfers network switches from overloaded controllers to those with spare capacity.
In simulations, the researchers demonstrated a detection accuracy of 93.7%. They obtained a true positive rate of 91.6% and a true negative rate of 87.5%. The researchers argue that combining traffic anomaly detection with automated load balancing could strengthen increasingly centralised network infrastructures.
Ahsan Shariff, M. and Nelson Kennedy Babu, C. (2026) ‘Traffic anomaly detection with wild geese dwarf mongoose optimisation_DQNN’, Int. J. Heavy Vehicle Systems, Vol. 33, No. 2, pp.147–172.
