An Intrusion Detection Model Based on Deep Belief Networks
Proposes an intrusion detection algorithm of support vector machine based on Deep Belief Networks for improving the traditional method in detection speed, accuracy, complexity, etc. The BP neural network structure will do a fine turning on parameters after double RBMS structure reducing the dimension of data, in this way, the corresponding optimal low-dimensional representation of raw data can be ob-tained. Support Vector Machine classification algorithm is to discriminate the intrusion from low-dimensional data. The experiments with NSL-KDD dataset show that the new algorithm is a feasible and effective intrusion detection model for IDS to provide a new way of think-ing.
Deep LearningIntrusion DetectionDeep Belief NetworksFeature ReductionSupport Vector Machine
NETL
NSTL
万方数据
维普
