Machine Learning-Assisted Measurement Device-Independent Quantum Key Distribution on Reference Frame Calibration.

Sihao Zhang,Xingyu Zhou,Jingyang Liu,Guigen Zeng,Qin Wang,Chunhui Zhang

doi:10.3390/e23101242

Abstract

In most of the realistic measurement device-independent quantum key distribution (MDI-QKD) systems, efficient, real-time feedback controls are required to maintain system stability when facing disturbance from either external environment or imperfect internal components. Traditionally, people either use a “scanning-and-transmitting” program or insert an extra device to make a phase reference frame calibration for a stable high-visibility interference, resulting in higher system complexity and lower transmission efficiency. In this work, we build a machine learning-assisted MDI-QKD system, where a machine learning model—the long short-term memory (LSTM) network—is for the first time to apply onto the MDI-QKD system for reference frame calibrations. In this machine learning-assisted MDI-QKD system, one can predict out the phase drift between the two users in advance, and actively perform real-time phase compensations, dramatically increasing the key transmission efficiency. Furthermore, we carry out corresponding experimental demonstration over 100 km and 250 km commercial standard single-mode fibers, verifying the effectiveness of the approach.

Highlights

Published: 24 September 2021Based on the laws of quantum physics [1], quantum key distribution (QKD) can in principle provide unconditional security between two legitimate users (Alice and Bob) [2].due to the loopholes of imperfect devices, the security of practical QKD systems are vulnerable to various attacks by an evil eavesdropper (Eve) [3,4,5]
The scheme keeps the stability of the QKD system at the cost of the so-called duty cycle [16], which refers to the ratio of the transmission time to the total
The whole data consists of the features and label of various time moments [24], including the operating temperature, the humidity, the intensity of a laser, the partially disclosed quantum bit error rate (QBER) of XX basis-pair, and five time-series displacement voltages, which can be obtained by running the measurement device-independent QKD (MDI-QKD) system with the traditional scanning-andtransmitting program

Summary

Introduction

Due to the loopholes of imperfect devices, the security of practical QKD systems are vulnerable to various attacks by an evil eavesdropper (Eve) [3,4,5]. Combined with the decoystate method, MDI-QKD can resist the loopholes from detector side-channel attacks and multi-photon components in sources, and has attracted extensive attention [9,10,11,12,13,14,15]. An original approach is using scanning-and-transmitting program to calibrate the phase drift. Bob scans his phase modulation voltage while Alice fixes her phase voltage to ascertain the zero-phase voltage of the minimum count. The scheme keeps the stability of the QKD system at the cost of the so-called duty cycle [16], which refers to the ratio of the transmission time to the total

Methods

Findings

Discussion

Conclusion