METHOD FOR ANALYZING RISK ELEMENT OF NETWORK PACKET BASED ON RECRUUENT NEURAL NETWORK AND APPARATUS ANALYZING THE SAME

摘要

The present invention relates to a technology for analyzing a risk factor of a network packet based on a circulating neural network, which comprises: a packet input unit for receiving continuous first and second packets in a session from a transmission end; a first risk factor determining unit for applying a circulating neural network model to the first packet to predict data characteristics of a subsequent packet, and determining a risk factor on the basis of similarity between the data characteristics of the subsequent packet and that of the second packet; a second risk factor determining unit for performing a risk analysis for the second packet to re-determine the risk factor when the similarity is less than or equal to a specific reference; and a circulating neural network learning unit for updating the circulating neural network model by performing the circulating neural network learning for the second packet when the re-determination is performed.