Network security threat analysis method and system based on LDA machine learning

Abstract

The invention discloses a network security threat analysis method and system based on document topic generation model (LDA) machine learning, and the method comprises the following steps: step 1, carrying out the data collection of different types of network flows in a data collection module according to a specific application scene; and step 2, in a machine learning calculation module, calculating the abnormal probability of network connection by using an LDA topic model machine learning algorithm; and step 3, in the operation analysis module, in combination with a threat intelligence database, detecting the attack type of the suspicious network connection by using a credibility detection-based method. Suspicious connection, abnormal flow and unknown attacks can be effectively detected.

Description

technical field [0001] The present invention relates to the field of network security, more specifically, to a network security threat analysis method and system based on machine learning of Document Topic Generation Model (LDA). Background technique [0002] Due to the rapid development of information technology, the Internet has become an indispensable tool in people's daily life and work. But the ensuing problem is that the widespread vulnerability of cyberspace will make it face a cybersecurity threat situation. [0003] Existing network security technologies center on vulnerabilities and perform network security detection based on signatures. By comparing network traffic with signatures, known vulnerabilities or known network attacks can be effectively detected. [0004] However, this method relies on the feature rule library, which needs to be continuously updated, and this detection cannot effectively prevent unknown threats or attacks. However, new attack methods a...

AI Technical Summary

Problems solved by technology

While the accuracy of these methods is sensitive to the number of topics, it may be easier to estimate the number of topics for a small corpus, but it is impractical to estimate the number of topics when the size of the corpus becomes large.

Images