Cloudx-Defnet – Cloud Xception Defense Network

In the evolving landscape of cloud computing, securing networks against cyber threats is a critical challenge. Traditional intrusion detection systems (IDS) often struggle with high false alarm rates and scalability issues. To address these concerns, we propose XKFHnet: Xception Kronecker Forward Fractional Net, a novel deep learning-based approach for intrusion detection in cloud environments. XKFHnet integrates the Xception architecture for enhanced feature extraction, the Kronecker product for efficient parameter optimization, and the Forward Fractional Network mechanism to improve gradient flow and convergence speed. This model effectively processes large-scale cloud traffic data, identifying both known and emerging threats with high precision. Extensive experimentation on benchmark datasets demonstrates that XKFHnet outperforms existing IDS models in terms of accuracy, precision, recall, and F1-score, while significantly reducing computational complexity. This research contributes to the development of intelligent, adaptive, and high-performance security frameworks tailored for modern cloud infrastructures.