Title: Optimised dual temporal gated multi-graph convolution network-based distributed denial of service attack detection in cloud computing

Authors: Ramesh Babu Putchanuthala; Gopisetty Naga Rama Devi; Prabha Murugesan; Muniyandy Elangovan; Radhika Rathanasalam; Ramasamy Senthamil Selvan

Addresses: Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Bowrampet, Hyderabad – 500043, Telangana, India ' Department of Computer Science, Data Science, Sreyas Institute of Engineering and Technology, Hyderabad, Telangana, 500068, India ' Department of Electronics and Communication Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science Technology, Chennai, Tamil Nadu 600062, India ' Department of Biosciences, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai – 602 105, India ' Department of Networking and Communications, School of Computing, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu – 600073, India ' Department of Electronics and Communication Engineering, Annamacharaya Institute of Technology and Sciences, Tirupati, Andhra Pradesh, India

Abstract: Distributed denial of service (DDoS) attacks are growing threat to network security, and existing methods attains higher false positive and false negatives when classifying attack and legitimate data, resulting in reduced accuracy. To overcome this, optimised dual temporal gated multi-graph convolution network-based fennec fox optimisation for distributed denial of service attack detection in cloud computing (DTGMGCN-DoS-ADD-CC) is proposed. Initially, data adaptive Gaussian average filtering (DAGAF) pre-processes the CICIDS2017 dataset to correct mismatched values. Then swarm optimisation algorithm (DSOA) selects the transformed features, it's used by multiple-graph convolution network with dual temporal gates (DTGMGCN) for precise detection of normal and attacked packet of information (API). The fennec fox optimisation (FFO) fine-tunes DTGMGCN's weight parameters, further boosting performance. Experimental results show that DTGMGCN-DoS-ADD-CC achieves 99.37% accuracy, 98.9% sensitivity, and 98.95% specificity, outperforming existing methods. The improvement highlights robustness and efficacy of the DTGMGCN-DoS-ADD-CC approach for DDoS attack detection in cloud computing.

Keywords: dual temporal gated multi-graph convolution network; fennec fox optimisation; FFO; cloud computing; distributed denial of service attack detection; machine learning.

DOI: 10.1504/IJBIC.2025.150628

International Journal of Bio-Inspired Computation, 2025 Vol.26 No.4, pp.207 - 219

Received: 28 May 2024
Accepted: 17 Dec 2024
Published online: 18 Dec 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article