IoT data feature extraction and intrusion detection system for smart cities based on deep migration learning

•IoT feature extraction and intrusion detection algorithm for intelligent city based on deep migration learning model is proposed.•The deep learning model is enhanced and optimized to be fit for the smart city scenarios.•Parameter transfer mines model parameters model is designed to establish connection between target task and source task.•Feature transfer focuses on finding a common feature representation implicit in source and target domain feature spaces.•The proposed model is tested on pubic massive complex data sets to validate the robustness.