<p>➀ The FedLLMGuard framework, developed by the University of Portsmouth, combines large language models (LLMs) and federated learning to enable real-time threat detection in 5G networks while preserving data privacy;</p><p>➁ It achieved 98.64% detection accuracy and responded to attacks in 0.0113 seconds, outperforming traditional intrusion detection systems;</p><p>➂ The system’s adaptability and self-learning capabilities address evolving cyber threats, offering a critical solution for securing next-generation wireless infrastructures.</p>