Secure wireless communication via adversarial machine learning: A Priori vs. A Posteriori

ICT Express

卷:8

Joonhyuk Kang¹  Sangwoo Park²  Junghaa Seo² 

[1] Corresponding author.;

[2] School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea;

关键词: Wireless communication;    Adversarial example;    Machine learning;    Modulation recognition;   

DOI  :  

来源: DOAJ

【 摘 要 】

This paper considers wireless communication system consisted of one transmitter, one legitimate receiver, and one eavesdropper. The transmitter transmits perturbation-added signal (i.e. adversarial example) with a certain modulation type, while the legitimate receiver and the eavesdropper adopt deep neural networks (DNN)-based classifier to recognize the modulation type of the received signal. Compared to the fact that the general goal of adversarial examples being a misclassification of all available classifiers, our objective is to design an adversarial example that lets the legitimate receiver classify accurately while the eavesdropper misclassifies. To this end, we propose two design approaches of the adversarial examples: (i)A priori; (ii)A posteriori, i.e. before and after learning steps of the receiver, respectively. Numerical results show that both approaches are effective for securing the communication link.

【 授权许可】

Unknown