Authors:
V. Revathi, Swathi Baswaraju, M. Arunadevi Thirumalraj, Piyush Kumar Pareek

Addresses:
Department of Research and Development, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Computer Science and Engineering (Data Science), New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Computer Science and Engineering, Karunya Institute of Technology and Science, Coimbatore, Tamil Nadu, India. Department of Computer Science and Business Management, Saranathan College of Engineering, Tiruchirappalli, Tamil Nadu, India. Department of Artificial Intelligence and Machine Learning, Nitte Meenakshi Institute of Technology, Bengaluru, Karnataka, India.

Abstract:

A new paradigm in networking, software-defined networking (SDN) separates control logic from forwarding operations, allowing for faster administration and better setup of network resources. New SDN allows for more security measures and drastically lowers the computational burden on devices associated to the internet of things (IoT) network. However, centralized network design raises security concerns, especially DoS attacks. Since SDN lacks message-verification, attackers can forge source address details to launch a denial-of-service attack. Ensemble Deep Learning and SDN are used to detect and mitigate Distributed Denial-of-Service assaults in this article. The proposed framework uses the bidirectional gated recurrent unit (BiGRU), transformer block, and convolutional neural network to develop an SDN-enabled security apparatus for IoT devices to detect and mitigate DDoS attacks. Wildebeest Herd Optimization (WHO) selects remote SDN controller and features to counter DDoS attacks utilizing Open Flow (OF) switches and reallocate network resources to permitted hosts. The experimental results show that the recommended framework surpasses current state-of-the-art techniques in DDoS detection accuracy and false alarm rate.

Keywords: Centralised Network; Detection and Mitigation; Open Flow; Convolutional Neural Network; Software-Defined Networking; Internet of Things; Optical Character Recognition.

Received on: 05/02/2025, Revised on: 15/04/2025, Accepted on: 05/06/2025, Published on: 22/11/2025

DOI: 10.69888/FTSCL.2025.000488

FMDB Transactions on Sustainable Computer Letters, 2025 Vol. 3 No. 4, Pages: 227-241

• Views : 28
• Downloads : 9

Download PDF