Securing Heterogeneous IoT With Intelligent DDoS Attack Behavior Learning
Nhu–Ngoc Dao, Trung V. Phan, Umar Sa’ad, Joongheon Kim, Thomas Bauschert, Dinh‐Thuan Do, Sungrae Cho
Abstract
The rapid increase of diverse Internet of Things (IoT) services and devices has raised numerous challenges in terms of connectivity, interoperability, and security. The heterogeneity of the networks, devices, and services introduces serious vulnerabilities to security, especially distributed denial-of-service (DDoS) attacks, which exploit massive IoT devices to exhaust both network and victim resources. As such, this article proposes FOGshield, which is a localized DDoS prevention framework leveraging the federated computing power of the fog computing-based access networks to deploy multiple smart endpoint defenders at the border of relevant attack-source/destination networks. Cooperation among the smart endpoint defenders is supervised by a central orchestrator. The central orchestrator localizes each smart endpoint defender by feeding appropriate training parameters into its self-organizing map component, based on the attacking behavior. Performance of the FOGshield framework is verified using three typical IoT traffic scenarios. Numerical results reveal that the FOGshield outperforms existing solutions.