Login

Deep Learning Based Communication: an Adversarial Approach
Ref: CISTER-TR-190605       Publication Date: 27 to 28, Jun, 2019

Deep Learning Based Communication: an Adversarial Approach

Ref: CISTER-TR-190605       Publication Date: 27 to 28, Jun, 2019

Abstract:
Deep learning based communication using autoencoder have revolutionized the design of physical layer in wireless communication. In this paper, we propose an adversarial autoencoder to mitigate vulnerability of autoencoder against adversarial attacks. Results confirm the effectiveness of adversarial training by reducing block error rate (BLER) from 90 percent to 56 percent.

Authors:
Yousef Emami
,
Rahim Taheri


Events:

DCE 2019
27, Jun, 2019 >> 28, Jun, 2019
3rd Doctoral Congress in Engineering
Porto, Portugal


Poster presented in 3rd Doctoral Congress in Engineering (DCE 2019).
Porto, Portugal.



Record Date: 4, Jun, 2019