Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Radio signal counterfeiting method for counterfeiting deep learning

A radio signal and deep learning technology, applied in neural learning methods, interference to communication, confidential communication, etc., can solve problems such as easy detection, large visual difference of fake signals, and inability to directly transfer signals, and reduce accuracy. Effect

Active Publication Date: 2021-05-28
XIDIAN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the large visual difference between the fake signal and the original signal, it is easy to be detected, so the existing methods cannot be directly transferred to the signal domain.

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
  • Radio signal counterfeiting method for counterfeiting deep learning
  • Radio signal counterfeiting method for counterfeiting deep learning
  • Radio signal counterfeiting method for counterfeiting deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] In electronic warfare, as the accuracy of signal classifiers based on deep learning continues to improve, the enemy's classification accuracy of radio signal modulation is getting higher and higher, and communication security is threatened. However, the existing data forgery methods against deep learning , which is mainly used against image classifiers in the field of computer vision. When used to forge signals, there will be a significant visual difference between the forged signal and the original radio signal. The enemy can identify the existence of the forged signal with the naked eye, reducing the deception of the forged signal properties, therefore, cannot be directly transferred to adversarial radio signal classifiers. From the perspective of eliminating the visual difference between the forged signal and the original radio signal, the present invention studies the radio signal forgery method for countering deep learning, proposes the visual limitation of signal f...

Embodiment 2

[0054]The overall technical scheme of the radio signal forgery method for combating deep learning is the same as that of embodiment 1, and the visual limitation of countering signal generation described in step (5) is applied to the differential evolution algorithm to obtain the signal-to-noise scheme set N', which is proposed by The visual restriction of counter signal generation, and the visual restriction is used in the differential evolution algorithm, by using the signal classifier M based on deep learning to evaluate the noise scheme, and finally generate the final population T' representing the signal-noise scheme set, see figure 2 , the specific implementation steps are:

[0055] (5a) Generate a population of offspring with visual constraints Applying the proposed visual constraints on adversarial signal generation to a differential evolution algorithm to generate offspring populations Generate a child population of the differential evolution algorithm for the pare...

Embodiment 3

[0071] The overall technical scheme of the radio signal forgery method for resisting deep learning is the same as embodiment 1-2, the evaluation noise scheme described in step (5b), is to adopt the signal classifier M based on deep learning, calculate T and The evaluation score of the middle noise scheme, the implementation steps include:

[0072] (5b1) Convert the interference scheme into a candidate countermeasure signal: the current parent population T and the child population The interference scheme in is transformed into a candidate countermeasure signal set X'=[x 1 ',...,x k ',...,x 800 '], where, 1≤k≤800, is the kth candidate adversarial signal, The conversion rules are:

[0073]

[0074]

[0075] (5b2) Obtain the evaluation score: input each candidate adversarial signal in the candidate counterfeit signal set to the signal classifier M based on deep learning to be adversarial, as the evaluation score of the corresponding interference scheme:

[0076] Sc...

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 provides a radio signal counterfeiting method for confronting deep learning, and solves the technical problem that a signal classifier based on deep learning is difficult to confront in the technical field of artificial intelligence and electronic confrontation. The method comprises the following steps: randomly generating candidate adversarial signals for modulated radio signals, taking the candidate adversarial signals as an initial parent population, and generating a signal interference scheme set through a differential evolution method based on visual limitation; and performing evaluation by adopting a radio signal classifier based on deep learning to obtain an interference signal and an adversarial signal, and completing adversarial signal counterfeiting. The forged signal and the original radio signal have extremely high similarity, a signal classifier based on deep learning is effectively resisted, and the radio signal modulation type classification precision is reduced. The counterfeited signal basically does not influence the understanding of the radio signal content under the condition that the interference signal is unknown. The method is used for electronic countermeasures in the military field to prevent radio signal modulation types from being identified.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and electronic countermeasures, and further relates to the forgery generation of radio signals, specifically a radio signal forgery method specially used to combat deep learning. In electronic countermeasures, it can effectively interfere with the enemy's deep neural network classifier's identification of our signal modulation type, further concealing our own attempts and improving the survivability of the equipment. The invention can be used for application and research in the field of military communication security. Background technique [0002] With the development of deep learning, the signal classifier based on deep learning has been significantly developed. For example, the accuracy rate of modulation classification of radio modulation signals with low signal-to-noise ratio has reached more than 90%. However, in electronic countermeasures, the improvement of the modulation ...

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
IPC IPC(8): H04K1/02H04K3/00G06N3/08G06N3/04G06K9/62
CPCH04K1/02H04K3/65G06N3/049G06N3/086G06N3/045G06F18/24
Inventor 杨淑媛马宏斌冯志玺王敏段韵章杨晨刘慧玲王能国孙泽培焦李成王翰林
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com