Network security blog classification method and system based on feature extraction

Abstract

The invention discloses a network security blog classification method and a network security blog classification system based on feature extraction. The method comprise calculating the non-dictionaryword density for each blog; calculating blog malicious tendencies for each blog; counting high-frequency words common to all blogs; calculating the frequency of each high-frequency word in each blog Inverse document frequency; based on the blog's non-dictionary word density, blog malicious tendencies, and the frequency of each high-frequency word in each blog-Inverse document frequency, and codingbased on the correlation or uncorrelation between blog and IOC to train the preset classification model to obtain a blog classifier; gettomg the non-dictionary word density of the blog to be categorized, blog malice, and the frequency of high-frequency words Reverse the document frequency and input to the trained blog classifier to obtain the classifier output value indicating that the blog to beclassified is related or not related to the IOC. Through the above method, IOC-related blogs and IOC-independent blogs in network security technology blogs can be accurately classified.

Description

technical field [0001] The invention belongs to the field of blog classification, and in particular relates to a feature extraction-based network security blog classification method and system. Background technique [0002] In recent years, cyber threats have expanded in scope and frequency. Many companies have suffered huge losses due to cyber attacks, and how to deal with complex and changeable cyber threats has become the focus of attention of various companies. After analyzing cyber threats, many cyber security experts publish the obtained cyber threat intelligence in blogs. Such blogs contain a large number of network threat indicators (Indicator of Compromise, referred to as IOC), such as malicious URLs, Trojan virus names, and the like. These IOCs represent the behavioral characteristics of network threats and play an important role in detecting and defending against network attacks. However, there are still many blogs related to news and security product promotion...

AI Technical Summary

Problems solved by technology

In our classification of network security blogs, our final categories are blogs related to IOC and blogs not related to IOC. However, among blogs not related to IOC, some blogs also describe cyber threats, but there is no comment on cyber threats. Behavioral characteristics analysis, such blogs and IOC-related blogs do not have a high degree of semantic distinction in the title, and existing methods cannot accurately identify them

Images