AI-Driven Threat Detection In 5G Edge computing environments Post-2024 Rollout

The massive increase in the Internet of Things gadgets and the extensive implementation of fifth-generation networks have already changed the world connectivity environments radically, as well as increasing the attack surface of advanced cyber attackers. The study introduces a thorough study of artificial intelligence-based threat detection systems and is specifically modelled to train in edge computing structures and architectures of the fifth-generation network in the post-2024 rollout stage. The proposed study suggests a new hybrid deep learning intrusion detection system that will combine Convolutional neural networks, Bidirectional Long short-term memory networks and Autoencoder networks together in a federated learning process that will facilitate the training of privacy-preserving collaborative models on distributed edge devices. The investigation will have positive outcomes to such intelligent, scalable, and adaptive security solutions to heterogeneous fifth-generation Internet of Things ecosystems that can enable computational constraints, privacy preservation needs, and real-time detection functions necessary to protect critical infrastructure and support autonomous operations in next-generation wireless networks.