.png){kind=icon}
.png){kind=icon}
Return
Multidimensional reconciliation scheme using deep learning in continuous-variable quantum key distribution
.png){kind=icon}
OA
AI
DOI：10.1088/1367-2630/adcf45.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Information reconciliation is a significant stage in continuous-variable quantum key distribution (CV-QKD) systems as it directly affects the performance of the CV-QKD systems including secret key rate and secure transmission distance. This paper proposes a multidimensional reconciliation scheme using deep learning in CV-QKD systems. Firstly, different neural networks are constructed to obtain the norm information. Secondly, a multidimensional reconciliation scheme with deep learning assisted norm information is proposed which no longer needs to transmit the norm information through the authenticated classical public channel. Finally, simulation results and performance analysis show that, compared with the traditional multidimensional reconciliation scheme, the multidimensional reconciliation scheme with deep learning assisted norm information can decrease the communication traffic to a certain extent.
Keywords:
multidimensional reconciliation
continuous-variable quantum key distribution
deep learning
low-density parity-check codes
Journal
IF:
2.8
Papers:
580
Citations:
3.5W
Organization
No organization information available