Intrusion Detection Algorithm for Industrial Control System Based on LSTM

Inhalt:
In view of the low recognition accuracy and high false alarm rate of current industrial control system intrusion detection methods, considering the periodicity and timing correlation of industrial control network traffic, an intrusion detection algorithm based on long and short-term memory networks is designed. The algorithm processes the network stream into a one-dimensional matrix, and after passing through the long and short-term memory cell layer, the one-dimensional matrix is input into the fully connected network, and the softmax layer is used to output the predicted probabilities of each category. Experimental results show that compared with the KNN and CNN, this algorithm improves the accuracy of intrusion detection, reduces the detection time, and can effectively detect intrusions against the industrial control systems.