Deep learning algorithms have been shown to be powerful in many communication network design problems, including that in automatic modulation classification. However, they are vulnerable to carefully crafted attacks called adversarial examples. Hence, the reliance of wireless networks on deep learning algorithms poses a serious threat to the security and operation of wireless networks. In this letter, we propose for the first time a countermeasure against adversarial examples in modulation classification. Our countermeasure is based on a neural rejection technique, augmented by label smoothing and Gaussian noise injection, that allows to detect and reject adversarial examples with high accuracy. Our results demonstrate that the proposed countermeasure can protect deep-learning based modulation classification systems against adversarial examples.

Countermeasures Against Adversarial Examples in Radio Signal Classification

Roli, Fabio
Ultimo
2021-01-01

Abstract

Deep learning algorithms have been shown to be powerful in many communication network design problems, including that in automatic modulation classification. However, they are vulnerable to carefully crafted attacks called adversarial examples. Hence, the reliance of wireless networks on deep learning algorithms poses a serious threat to the security and operation of wireless networks. In this letter, we propose for the first time a countermeasure against adversarial examples in modulation classification. Our countermeasure is based on a neural rejection technique, augmented by label smoothing and Gaussian noise injection, that allows to detect and reject adversarial examples with high accuracy. Our results demonstrate that the proposed countermeasure can protect deep-learning based modulation classification systems against adversarial examples.
2021
Modulation; Perturbation methods; Receivers; Training; Smoothing methods; Radio transmitters; Noise measurement; Deep learning; adversarial examples; radio modulation classification; neural rejection; label smoothing
File in questo prodotto:
File Dimensione Formato  
Countermeasures_Against_Adversarial_Examples_in_Radio_Signal_Classification-3.pdf

Solo gestori archivio

Tipologia: versione editoriale
Dimensione 983.55 kB
Formato Adobe PDF
983.55 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
postprint+radiosignal(3) (2).pdf

accesso aperto

Tipologia: versione post-print
Dimensione 2.71 MB
Formato Adobe PDF
2.71 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/390443
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 14
social impact