Deep learning network intrusion detection method based on improved learning rate

Abstract

The invention relates to a deep learning network intrusion detection method based on an improved learning rate. Determination method for learning rate and iteration frequency of improved deep belief network model in training is adopted, and the advantages of the improved deep belief network model and a softmax regression function are utilized to establish a deep belief network for network intrusion detection; and the softmax multi-classification combination model is used for training the model by using the public training data of the network intrusion detection data set and identifying and classifying the test data of the network intrusion detection data set by using the trained model. Rapid convergence of model parameters is realized by using an adaptive learning rate, and the optimized deep belief network-softmax multi-classification combination model is used for an intrusion detection system, the identification accuracy of attack behaviors can be effectively improved, and meanwhilethe detection efficiency can be improved.

Description

technical field [0001] The invention relates to the field of intrusion detection network security, in particular to a deep learning network intrusion detection method based on improved learning rate. Background technique [0002] Intrusion detection technology is an important network security defense method to protect user privacy and data. In order to effectively identify various network attacks, previous researchers have introduced various machine learning methods into intrusion detection and made breakthroughs. However, traditional shallow machine learning methods are limited by time and space when faced with the classification of massive network data, which reduces the efficiency of security protection. Therefore, it is of great significance to study efficient and feasible intrusion detection methods to improve network security. [0003] Based on this, the research of intrusion detection methods for massive data focuses on feature learning and dimensionality reduction. ...

AI Technical Summary

Problems solved by technology

[0004] In general, training a DBN is a computationally complex process because it involves independently training several RBM networks, which tends to fall into local minima, slow convergence, and difficult model training.

As the amount of data increases, the error brought about during training will become larger and larger, and the accuracy of prediction will also decrease.

Images