Security policy optimization processing method and device based on big data

Abstract

The invention discloses a security policy optimization processing method and device based on big data. The method comprises the steps of obtaining an uploaded log file uploaded by a user and a prevention strategy corresponding to the log file; under the condition that the number of the log files corresponding to the predetermined prevention rules reaches a threshold value, inputting the log files and the prevention rules as training data into a pre-configured machine learning model for training to obtain a training model corresponding to the prevention rules; inputting the to-be-identified log file into a plurality of training models respectively, and obtaining a probability value of the log file corresponding to each training model; and prompting the combined prevention strategy to an uploader of the predetermined log file. According to the method and device, the problems of inaccurate manual definition of the prevention strategy for the network attack and lack of training data for making the prevention strategy through the machine learning training model in the prior art are solved, and the dependence on people in the process of making the prevention strategy is reduced.

Description

technical field [0001] The present application relates to the field of machine learning, and in particular, to a method and apparatus for optimizing a security policy based on big data. Background technique [0002] In the prior art, there are various types of network attacks. At present, the prevention of network attacks basically relies on manual formulation of strategies. This requires every network administrator to have extensive experience, which is impossible to some extent. [0003] With the development of machine learning, many machine learning models have been open sourced. A very important premise is that a large amount of training data is required to formulate a network attack defense strategy through machine learning. Network attacks and their corresponding defense strategies are generally not easy to obtain as training data as a single administrator. Therefore, the machine learning model is easy to build, but the difficulty is how to obtain a large amount of ...

AI Technical Summary

Problems solved by technology

[0005] This application provides a big data-based security policy optimization processing method and device to solve the problems in the related art that the manual definition of defense policies against network attacks is not precise enough and the prevention policies are lack of training data through machine learning training models

Images