Hybrid deep learning based intelligent security architecture for web threat mitigation in mobile communication networks

Résumé fourni par la source

In the current artificial intelligence era, mobile network channels play a crucial role in the development of networks with 4G, 5G, and next generation 6G. This research focuses on intellectual security architecture (ISA) to mitigate web-oriented attacks that use hybrid deep learning models to stall the operation of mobile networks. With the rapid evolution of mobile communication systems, especially in the context of edge-based content sharing, network security has become a crucial aspect of maintaining robust and reliable service. The integration of artificial intelligence (AI) into security frameworks has opened new frontiers in identifying and mitigating cyber threats such as web-based attacks. This research suggests a deep learning system that uses lightweight bidirectional long short-term memory (Bi-LSTM) networks and transformer-based multi-head attention (MHA) to smartly detect web attacks. Apart from dataset accuracy, the proposed ISA is assessed for edge feasibility through testing. The ISA architecture requires 30,087 parameters and 0.42 MB of storage with a medium inference latency under 90 ms, thereby supporting on device deployment on limited storage 6G edge node. The proposed model is evaluated on a labeled web traffic dataset and trained using an additional zero shot, cross-dataset evaluation on independent edge IIoT dataset. The proposed model preserves effective attack/normal separability AUC of 0.93% without any domain specific fine tuning. Additionally, the proposed ISA model is very good at predicting different web attacks such as brute force, SQL injection, and background shell attacks, achieving an accuracy of 97%, while other models like multioutput Cat-Boost and Char-LSTM achieved accuracies of 88% and 85%, respectively. The proposed hybrid model performs well in predicting web attacks which indicates the learned representation generalized beyond its training distribution and ISA is suitable for lightweight and federated adaption on edge devices.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.