IoT Security Detection Method Based on Multifeature and Multineural Network Fusion

Abstract

IoT security detection plays an important role in securing the IoT ecosystem. The current detection systems suffer from poor fault tolerance and inefficient detection results. To address the IoT security vulnerability, the paper designs a multifeature fusion-based IoT security detection model to simulate an attacker sending test commands to IoT nodes. Firstly, the data collection algorithm is introduced, and the collected dataset is analyzed by three neural network models, namely, RNN, LSTM, and GRU, respectively. The best scoring model is selected as the classifier to identify vulnerabilities and achieve IoT security detection.