Network threat intelligence automatic extraction method based on deep learning

Abstract

The embodiment of the invention provides a network threat intelligence automatic extraction method based on deep learning, which can obtain intelligence source data and judge the data structure type of the intelligence source data. If the data structure type is an unstructured type, inputting the intelligence source data into a pre-trained intelligence entity identification model to obtain each intelligence entity in the intelligence source data, the intelligence entity identification model being a neural network model obtained by training based on preset characters and front and back positionconstraint conditions of the characters by using the intelligence sample data; and according to a preset combination form, combining the information entities to obtain the network threat information.According to the invention, a pre-trained information entity identification model can be used to carry out automatic extraction of network threat information; and the position constraint conditions introduced by the information entity identification model during training limit the front-back position relationship of the characters in the information entity, so that the out-of-order result of theinformation entity is reduced, and the accuracy of network threat information identification is improved.

Description

Technical field [0001] The invention relates to the technical field of network security, in particular to a method for automatically extracting network threat intelligence based on deep learning. Background technique [0002] With the rapid development of Internet technology, all kinds of data are uploaded to the Internet, and network information security has become a focus of various organizations. In order to avoid threats to themselves, it is necessary to defend against attacks by attackers. In network security defense methods, the use of known network threat intelligence to defend against unknown threats is an active defense method that uses detection and analysis as a means. Threat intelligence is knowledge based on evidence, including scenarios, mechanisms, indicators, meanings, and actionable recommendations. This knowledge is intelligence information related to threats faced, and there is evidence that the organization may be threatened. Cyber ​​threat intelligence is th...

AI Technical Summary

Problems solved by technology

The current method of intelligence extraction is prone to the prediction results of intelligence entities out of order, which makes the accuracy of network threat intelligence identification low.

Images