Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Opto-Electronics and Communications Conference (OECC)

High-Speed Long-Range Physical-Layer Key Distribution Assisted by Neural Networks

Xinran Huang, Liuming Zhang, Zhi Chai, Zanwei Shen, Weisheng Hu, Xuelin Yang

Published Jul 2, 2023• 2 citations
Publisher

Abstract

We propose and demonstrate the unidirectional physical-layer secure key generation and distribution in fiber networks using neural networks, with a Gb/s key generation rate demonstrated over 100-km standard single-mode fiber.
DOI
10.1109/oecc56963.2023.10209734

Related papers

Gb/s physical-layer secure key generation and distribution in fiber communications

Liuming Zhang, Xinran Huang, Erich Leitgeb +1 more

We present the high-speed physical-layer secure key generation and distribution in fiber networks. A key generation rate of 2.7 Gb/s is achieved over 10 km single-mode fiber using a specifically-designed bidirectional polarization scrambler.

International Conference on Optical Communications and Networks (ICOCN)•Aug 23, 2021•0 citations

Gb/s Secure Key Distribution Based on Synchronization of Polarization States

Liuming Zhang, Weisheng Hu, Xuelin Yang

We propose and demonstrate a high-speed physical-layer key distribution in fiber networks using synchronization of polarization states. An error-free and true random key generation rate of 2 Gb/s is achieved over 20 km single-mode fiber.

Optical Fiber Communication Conference•Jan 1, 2021•0 citations

A 300 km fiber channel mapping using neural networks for Gb/s physical-layer key distribution

Xinran Huang, Xinyong Peng, Liuming Zhang +2 more

Physical-layer secure key distribution (PLSKD) generally acquires highly correlated entropy sources via bidirectional transmission to share the channel reciprocity. For long-haul fiber links, the non-negligible backscattering noise (BSN) and the challenge of bidirectional optical amplification degrade the key generation performances. Since the channel reciprocity can be precisely mapped using neural networks (NNs), unidirectional PLSKD provides a feasible PLSKD for longer fiber links. Here, a final error-free key generation rate (KGR) in unidirectional PLSKD of 3.07 Gb/s is demonstrated over a 300 km fiber link using NNs. Moreover, the channel mapping is analyzed in terms of fiber distance, chromatic dispersion, the nonlinearity of random source, and BSN.

Optics Letters•Dec 6, 2023•10 citations

Fiber Mapping Using Neural Networks for Physical-Layer Secure Key Distribution

Yuhao Zhong, Xinran Huang, Zhi Chai +2 more

Neural networks are applied for fiber mapping in unidirectional physical-layer key distribution, where the bi-directional long short-term memory increases the key generation rate from 12.28 to 13.68 Gbps.

International Conference on Optical Communications and Networks (ICOCN)•Jul 26, 2024•1 citation

Physical Layer Cryptography Key Generation by Estimating Channel Characteristics based on Neural Network

Kun Wu, Yuefeng Ji, Hongxiang Wang

A physical-layer secure key generation scheme based on neural network is proposed. It can efficiently generate symmetric keys with high entropy, adjustable generation rate under the transmission distance of 100 km and bit-rate of 100Gbps.

Asia Communications and Photonics Conference•Jan 1, 2021•0 citations

906-Gb/s, 100-km Physical-layer Key Distribution Based on Unclonable Random Fiber Grating and Channel Reciprocity

Taihang Qiu, Xiangpeng Xiao, Qiang Lu +6 more

We experimentally demonstrate a physical-layer key distribution scheme based on unclonable random fiber gratings and optical link channel reciprocity. The distribution distance is 100km and the distribution rate reaches 9.06 Gb/s.

Conference on Lasers and Electro-Optics•Jan 1, 2024•0 citations
Physical-layer secure key distribution (PLSKD) generally acquires highly correlated entropy sources via bidirectional transmission to share the channel reciprocity. For long-haul fiber links, the non-negligible backscattering noise (BSN) and the challenge of bidirectional optical amplification degrade the key generation performances. Since the channel reciprocity can be precisely mapped using neural networks (NNs), unidirectional PLSKD provides a feasible PLSKD for longer fiber links. Here, a final error-free key generation rate (KGR) in unidirectional PLSKD of 3.07 Gb/s is demonstrated over a 300 km fiber link using NNs. Moreover, the channel mapping is analyzed in terms of fiber distance, chromatic dispersion, the nonlinearity of random source, and BSN.