Design method of intrusion detection system based on Bayesian neural network

Abstract

The invention provides a design method of an intrusion detection system based on a Bayesian neural network. According to the method, the intrusion detection system builds, trains, verifies and tests a Bayesian neural network model after carrying out related preliminary preprocessing of ETL, feature engineering and the like on data, and carries out related parameter tuning work. The intrusion detection system adopts an unsupervised learning model, not only does not need label data, but also can detect unknown network attacks, and plays a particularly important role in a network attack defense system.

Description

technical field [0001] The invention belongs to the technical field of intrusion detection, in particular to a design method of an intrusion detection system based on a Bayesian neural network. Background technique [0002] The proportion of attack incidents in the data of the Internet of Vehicles and the Internet of Things is very small, reflecting obvious data imbalance, and some attack data are related before and after, which may be short-term or long-term, and the actual attack methods are various. , lack of labeled data, so the intrusion detection and classification prediction of this type of data is a difficult point. [0003] Intrusion detection, as its name implies, is the detection of intrusions. It collects and analyzes information from several key points in the computer network or computer system, and finds out whether there are signs of violations of security policies and attacks in the network or system. The combination of software and hardware for intrusion d...

AI Technical Summary

Problems solved by technology

The disadvantage of the host-based intrusion detection system is that it depends on the specific system platform

[0006] From the perspective of machine learning, hidden Markov models (HMM) or long-term short-term memory (LSTM) models are often used to process time series data, but hidden Markov models are models based on homogeneous Markov assumptions. The state of LSTM only depends on the state of the previous moment, so it is not very good at processing and predicting important events with long intervals and delays in time series, and the LSTM model is mainly used for time series data with long intervals and delays, but generally for a supervised learning model

Images