Deep Learning Based Network Intrusion Detection

With the advancement of the times, the network has become an important part of people’s daily life, and its connection with our daily life of clothing, food, housing, transportation, medical education has become increasingly close. However, while the network brings us a richer and faster life, the network security problem is also becoming more and more prominent. Network security risks are posing new challenges to the economy, politics, ecology, national security, science and technology development and other fields, and the network security problem has received wide attention, and network intrusion detection, as an important part of the network security field, needs more attention from us. To further improve the performance of feature extraction for network intrusion data, a combined model based on convolutional neural networks and long short-term memory units is proposed for the problems of gradient disappearance and gradient explosion of ordinary neural networks, and also the improved seagull optimization algorithm is applied to the optimization of the model parameters, and Batch Normalization and Adam optimizer, thus constructing an efficient model.