Method, device, memory and processor for determining network attack type

Abstract

The application discloses a method, a device, a memory and a processor for determining a network attack type. The method includes: obtaining a log file uploaded by a user and a label of the log file; classifying; inputting the log file and the label corresponding to the log file as training data into a pre-configured machine learning model for training to obtain an attack corresponding to the attack type the training model; obtain the predetermined log file; respectively input the predetermined log file into multiple training models, and determine the attack type corresponding to the largest probability value as the attack type corresponding to the predetermined log file; the determined attack type Prompt to the uploader of the scheduled log file. This application solves the problems of possible deviations in the related technologies of manually identifying network attack types and the lack of training data for machine learning to identify network attack types, thereby improving the identification effect of network attack types.

Description

technical field [0001] The present application relates to network security, in particular, to a method and device for determining a network attack type, as well as a memory and a processor. Background technique [0002] In the prior art, there are various kinds of network attacks, and effective protection can be carried out only if the types of network attacks can be correctly judged. At present, the judgment of the type of network attack basically relies on manual judgment. This requires every network administrator to have rich experience, which is impossible to some extent. [0003] With the development of machine learning, many machine learning models have been open sourced. There is an important prerequisite for judging the type of network attack through machine learning. This prerequisite is the need for a large amount of training data. The training data of network attacks is generally not easy to obtain as a single administrator. Therefore, the machine learning mode...

AI Technical Summary

Problems solved by technology

[0005] The present application provides a method and device for determining the type of network attack, as well as a memory and a processor, so as to solve the problems in the related art that there may be deviations in the identification of the type of network attack manually and the lack of training data for identifying the type of network attack by machine learning

Images