Please wait a minute...
Computer & Telecommunication
Current Issue | Archive | Adv Search |
Model-based Robust RecognitionAlgorithm for Deep Learning Communication Signals
South-Central University for Nationalities
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      
Abstract  Deep learning is a hot topic in computer vision and natural language processing. In many applications, the performance of deep neural networks (DNN) is better than traditional methods, and has been successfully applied to tasks such as modulation classification and radio signal representation learning. In recent years, studies have found that deep neural networks are vulnerable to adversarial attacks and lack robustness to "adversarial examples". Regarding the robustness of the neural network communication signal recognition algorithm, the author regards the data that has been attacked by the PGD as model-based data, and inputs the data into the neural network, which makes the signal recognition and classification results wrong. Then with the help of model-based defense algorithms, which are robust training algorithm and adversarial training algorithm, the experimental results after training show that both methods have good defense effects.
Key wordsdeep learning      adversarial attack      model      signal recognition     
Published: 10 January 2021

Cite this article:

LIN Long. Model-based Robust RecognitionAlgorithm for Deep Learning Communication Signals. Computer & Telecommunication, 2021, 1(1): 20-22.

URL:

http://www.computertelecom.com.cn/EN/     OR     http://www.computertelecom.com.cn/EN/Y2021/V1/I1/20

[1] LIU Feng. Research and Practice of UI Talent Training Model under the Background of Integration of Production and Education[J]. 电脑与电信, 2021, 1(1): 64-66.
[2] GE Shi-xin. Research on Intelligent Media Industry Reform and Management Mode Innovation in 5G Era[J]. 电脑与电信, 2020, 1(9): 53-55.
[3] XIAO Cheng-wei. Design of the G.657 Single-mode Fiber Based on OptiFiber Simulation System[J]. 电脑与电信, 2020, 1(8): 36-40.
[4] YAN Lei. Study on the Deep Learning Diagnosis and Intervention of Online Courses for Higher Vocational College Enrollment Students under LearningAnalysis Technology[J]. 电脑与电信, 2020, 1(6): 30-33.
[5] YIN Hong-mei. Analysis and Construction of Intelligent Campus Based on IPv6[J]. 电脑与电信, 2020, 1(6): 63-65.
[6] YANG Jing. Innovative and Entrepreneurial Cross-border E-commerce Training Mode for Private Universities in Shaanxi Province[J]. 电脑与电信, 2020, 1(4): 1-4.
[7] . Time Window Setting on PredictionAccuracy of Rock Pressure in Fully Mechanized Working Face[J]. 电脑与电信, 2020, 1(4): 14-18.
[8] ZHENG Shao-lan. Application of Flipping Class in 3DSMAX Modeling Technology Course[J]. 电脑与电信, 2020, 1(4): 27-29.
[9] ZHANG Gang , CHEN Jia-lian, SONG Jian, GUO Jun-qi, ZHOU Chen-rui. Chinese Landscape Painting Automated Generation Model Based on Generative Adversarial Networks[J]. 电脑与电信, 2020, 1(3): 1-.
[10] LIN Hai. Design and Implementation of College Logistics Repair Application System Based on .Net Technology[J]. 电脑与电信, 2020, 1(3): 47-51.
[11] YANG Zhen-lin. Low Complexity LDPC Decoder Based on Deep Learning[J]. 电脑与电信, 2020, 1(3): 62-65.
[12] ZHANG Jing. Development of "Three DimensionalAbility"Assessment System in Higher Vocational Colleges[J]. 电脑与电信, 2020, 1(1-2): 22-24.
[13] LI Wei-hong. Exploration on the Professional Development Mode of Computer Network Technology under the 1+ X Certificate Mode — — TakingAnhui Forestry Vocational and Technical College for Example[J]. 电脑与电信, 2020, 1(12): 7-9.
[14] LIN Yu-man PAN Rou HUANG Jing-yi. Design of the Digital Tour of Nanhua Temple[J]. 电脑与电信, 2020, 1(12): 28-31.
[15] HOU Yan. Research and Design of the Network Security Model in Cloud Environment[J]. 电脑与电信, 2020, 1(12): 69-71.
Copyright © Computer & Telecommunication, All Rights Reserved.
Powered by Beijing Magtech Co. Ltd