IoT attack detection using quantum deep learning in large-scale networks

The probability of a cyberattack rises at an exponential pace in direct proportion to the size of the network-connected device population. Cybercriminals will concentrate their efforts on wireless networks because it is anticipated that more than half of all data on the Internet would originate from wireless networks. In this chapter, we develop an IoT attack detection using an intrusion detection system (IDS) framework that develops a quantum convolutional neural network-based Long Short-Term Memory (QCNN-LSTM) in large-scale networks. The collection of network logs is initially pre-processed and then it is classified using classifiers. The model is simulated to test its robustness against different scale of attacks, and the results show higher level of accuracy in detecting the attacks using QCNN-LSTM than other methods.