With the accelerating process of social informatization,our personal information security and Internet sites,etc.,have been facing a series of threats and challenges.Recently,well-developed neural network has seen gre...With the accelerating process of social informatization,our personal information security and Internet sites,etc.,have been facing a series of threats and challenges.Recently,well-developed neural network has seen great advancement in natural language processing and computer vision,which is also adopted in intrusion detection.In this research,a hybrid model integrating Multi-Scale Convolutional Neural Network and Long Short-term Memory Network(MSCNN-LSTM)is designed to conduct the intrusion detection.Multi-Scale Convolutional Neural Network(MSCNN)is used to extract the spatial characteristics of data sets.And Long Short-term Memory Network(LSTM)is responsible for processing the temporal characteristics.The data set used in this experiment is KDDCUP99 with different probability distributions in the training set and test set involving some newly emerging attack types,making the data more realistic.As a result,this type of data set is widely applied in the simulation experiment of intrusion detection.In this experiment,the assessment indices such as the accuracy rate,recall rate and F1 score are introduced to check the performance of this model.展开更多
文摘With the accelerating process of social informatization,our personal information security and Internet sites,etc.,have been facing a series of threats and challenges.Recently,well-developed neural network has seen great advancement in natural language processing and computer vision,which is also adopted in intrusion detection.In this research,a hybrid model integrating Multi-Scale Convolutional Neural Network and Long Short-term Memory Network(MSCNN-LSTM)is designed to conduct the intrusion detection.Multi-Scale Convolutional Neural Network(MSCNN)is used to extract the spatial characteristics of data sets.And Long Short-term Memory Network(LSTM)is responsible for processing the temporal characteristics.The data set used in this experiment is KDDCUP99 with different probability distributions in the training set and test set involving some newly emerging attack types,making the data more realistic.As a result,this type of data set is widely applied in the simulation experiment of intrusion detection.In this experiment,the assessment indices such as the accuracy rate,recall rate and F1 score are introduced to check the performance of this model.
