Unlock instant, AI-driven research and patent intelligence for your innovation.

Master User Simulation Attack Detection Method Based on Reinforcement Learning Algorithm

A technology of enhanced learning and simulated attack, applied in electrical components, safety devices, transmission systems, etc., can solve problems such as inability to obtain detection performance, and achieve good application prospects, improved detection performance, and high detection probability.

Active Publication Date: 2020-04-28
ZHEJIANG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the channel environment changes, the PUEA detection method based on signal characteristics with preset thresholds cannot obtain good detection performance

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
  • Master User Simulation Attack Detection Method Based on Reinforcement Learning Algorithm
  • Master User Simulation Attack Detection Method Based on Reinforcement Learning Algorithm
  • Master User Simulation Attack Detection Method Based on Reinforcement Learning Algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in further detail below with reference to the accompanying drawings and examples.

[0039] This example works on a CRN where the channel environment changes, such as figure 1 As shown, the environment meets the following conditions:

[0040] (1) In each time slot, in order to ensure that there is no communication conflict, there is at most one user in the CRN area that transmits signals and occupies the spectrum;

[0041] (2) In the kth time slot, the working probability of the PU is p; when the PU is not working, the MU launches an attack with the probability q, where q≤1-p;

[0042] (3) SU receives signals from PU and MU considering the influence of channel multipath fading;

[0043] (4) In each time slot, the benefit of SU using the idle spectrum is G, and the cost of causing interference to the primary user network is C.

[0044] Such as figure 2 , this example is implemented through the following steps:

[0045] Step 1....

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 invention relates to a main user simulation attack detection method based on a reinforcement learning algorithm. In an existing method, when a channel environment of a CRN (Cognitive Radio Network) is changed, detection performance can be obviously reduced. According to the method disclosed by the invention, decision detection threshold values in different channel environments are learned on line by a Q-learning algorithm, i.e., a channel multi-path time-delay difference is used as a state parameter, a decision threshold is used as an action policy and a long-time detection earning is used as a reward function of a system, and according to a feedback reward and punishment value of a management mechanism in each period, the decision threshold is regulated in real time by the Q-Learning algorithm. According to the method disclosed by the invention, the decision threshold is dynamically regulated by the Q-Learning algorithm, a PU (Primary User) feature parameter does not need to be used as prior information, detection performance in a case that the channel environment is changed can be effectively promoted, and the hardware configuration of an existing SU (Secondary User) does not need to be changed.

Description

technical field [0001] The patent of the present invention belongs to the technical field of cognitive radio security, and relates to a method for detecting a primary user simulation attack based on an enhanced learning algorithm when the channel environment changes. Background technique [0002] Cognitive Radio Network (CRN) can effectively utilize idle spectrum resources and improve resource utilization through a dynamic spectrum access mechanism. Dynamic spectrum access requires the secondary user (SU) to obtain idle spectrum information through spectrum sensing technology and access it opportunistically without interfering with the normal operation of the authorized user (Primary User, PU) in a certain frequency band. However, the dynamic spectrum access mechanism introduces unique security issues to CRN, and Primary User Emulation Attack (PUEA) is one of the typical attacks. In PUEA, a malicious user (Malicious User, MU) imitates the signal characteristics of the PU to...

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 Patents(China)
IPC IPC(8): H04L29/06H04W12/00H04W16/10
CPCH04L63/1441H04W12/00H04W16/10
Inventor 陈惠芳谢磊马向荣
Owner ZHEJIANG UNIV