Real-Time IoT Cybersecurity using Machine Learning-based AI Threat Detection System to Train Generative Robots

Abstract

Existing security protocols encounter major cybersecurity difficulties because the online devices' growing popularity continues to spread across networks. These security protocols are ineffective because they do not properly handle current cyber threats. The main goal of this study involves developing enhanced IoT cybersecurity through the development of a threat detection system which brings together adversarial training and deep learning models (CNN-LSTM) and Federated Learning (FL). The system enables distributed Internet of Things devices to work on security model development through Federated Learning while maintaining total privacy of their information. Security procedures controlled by generative artificial intelligence robots alongside real-time attack protection functions decrease security response durations. Through its Federated CNN-LSTM model the system upholds a 1.2% false positive rate alongside a 98.3% accuracy evaluation and 160 milliseconds of exact threat tracking time. The designed system sustains a minimal occurrence of incorrect alarm activations. The developed system provides real-time security for the Internet of Things framework because it enables adaptive protection systems while preserving user privacy in current IoT settings.