A network security defense method based on a Bayesian improved model

A network security, model technology, applied in the direction based on specific mathematical models, computing models, instruments, etc., can solve problems that have not been better studied

Inactive Publication Date: 2019-05-03
HUNAN UNIV
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] A large number of existing studies have used repeated games to study network attack and defense. However, how to more accurately estimate user identities and strategies in fraudulent attacks, and how to use historical interaction information to predict user behavior has not yet been better understood. Research

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A network security defense method based on a Bayesian improved model
  • A network security defense method based on a Bayesian improved model
  • A network security defense method based on a Bayesian improved model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] Hereinafter, the present invention will be further described in detail with reference to the drawings and specific embodiments.

[0068] An intelligent evaluation method for network security based on game theory includes the following steps:

[0069] Step 1. The defender sets the parameters of the income matrix and uses the Bayesian model to solve the convergence point Said Expressed as

[0070] Step 2. The defender sets the parameter a according to the demand, and the a is the probability that the attacker with N (ordinary user) identity adopts the C (conventional) strategy, and the historical revenue model is used to solve the convergence point Said Is the convergence point of the historical return model, expressed as x∈(0,1) in Time value.

[0071] Step 3: Defender settings (Choose the cumulative relative returns of strategies H and R) initial value (equivalent to setting α 0 , Which is the initial confidence of malicious users). Waiting for user access.

[0072] Step...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The objective of the invention is to solve the problem of how to utilize intrusion detection and honeypots to make decisions for fraudulent attacks and defenders. Therefore, the network security intelligent assessment method based on the game theory is provided, interaction between a malicious user and a defender is modeled into a multi-time game model, and fraudulent behaviors of the malicious user are depicted through a Bayesian model. a Bayesian improvement model is proposed according to the relative historical revenue model of the malicious user. According to the model, through data collection and analysis of each round of game condition, the defenders make an optimal choice, the attack cost of the attackers is improved, the attack frequency is reduced, and the network security is improved.

Description

Technical field [0001] The invention relates to a method for network security assessment, in particular to a network security defense method based on a Bayesian improved model for fraudulent attacks. Background technique [0002] Among the network security technologies based on detection, honeypot is a more mature detection technology, and has received a lot of progress in research. The honeypot itself is also a kind of resource. The difference from the conventional system is that the "value information" in it is all false information set by itself. The purpose of honeypot design is to be scanned and attacked by attackers, to induce attackers to carry out a series of attack methods in a well-arranged system, as long as the damage to the real system is controlled within an acceptable range. The honeypot can collect, monitor and analyze the attacker's attack behavior information in the honeypot. Using this effective information, the real system can be upgraded in advance. [0003] ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): H04L29/06G06N7/00
Inventor 王涛李连阳熊伟明
Owner HUNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products