Mitigating Network Attacks in IoT-SDN Using Deep Recurrent Residual Neural Networks with 5G-Enabled VANET Integration

Abstract

The rise of the Internet of Things (IoT) and Software-Defined Networking (SDN) has enhanced connectivity and control but also exposed networks to a wide range of security threats. IoT devices are great targets for hackers as their limited computational resources and security procedures reflect their nature. This link also introduces major security concerns. These devices can be used as points of access for attack on SDN infrastructure, which, in spite of their advantages, should be compromised cause of a single point of failure. This paper proposes a novel approach to mitigating network attacks in IoT-SDN environments using Deep Recurrent Residual Neural Networks (DRRNNs). By leveraging the predictive capabilities of DRRNNs, we detect and mitigate both known and emerging attack patterns with high accuracy. The integration of 5G technology enhances real-time data processing and communication, while the inclusion of Vehicular Ad Hoc Networks (VANET) extends the security framework to intelligent transportation systems. Our approach enables efficient threat detection and response in complex, large-scale IoT-SDN-5G networks, making it particularly suited for applications such as smart cities and autonomous driving. Simulation results demonstrate significant improvements in attack detection rates, network performance, and system resilience compared to existing models.