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

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.