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

Asia Communications and Photonics Conference

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

Kun Wu, Yuefeng Ji, Hongxiang Wang

Published Jan 1, 2021• 0 citations
Publisher

Abstract

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.
DOI
10.1364/acpc.2021.w3b.6

Related papers

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

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

Xinran Huang, Liuming Zhang, Zhi Chai +3 more

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.

Opto-Electronics and Communications Conference (OECC)•Jul 2, 2023•2 citations

A Novel Physical Layer Key Generation Method Based on WGAN-GP Adversarial Autoencoder

Jingyuan Han, Yi Zhou, Gang Liu +2 more

The reciprocity of wireless channel between legitimate nodes is the premise of physical layer security key generation. Deep neural networks provide the non-linear transformation method to extract symmetric keys from reciprocal channel responses and show better freedom and performance than traditional methods. However, the hidden layer output in neural networks is unpredictable and the extracted high-dimensional features can not be estimated in advance, which is difficult to be applied to the key generation in the physical layer. In this paper, the key generation method based on WGAN-GP adversarial autoencoder is proposed to extract features efficiently between legitimate nodes, and the features can be fitted to the Gaussian distribution. Meanwhile, the Wasserstein distance and gradient penalty are applied in the game training to solve the gradient explosion. Compared with the PCA method, the proposed method has higher security key capacity, lower key error rate, and no interaction in the key generation process, which avoids key leakage.

International Conference on Communications, Information System and Computer Engineering (CISCE)•May 27, 2022•8 citations

Unidirectional physical layer secure key distribution in a fiber channel assisted by neural networks

Liuming Zhang, Xinran Huang, Zhi Chai +3 more

Physical layer secure key distribution (PLSKD) in fiber networks provides high-level security originating from the channel uniqueness, while the channel reciprocity is shared between the legal users via bidirectional transmission. To ensure the key consistency, perfect wideband bidirectional optical devices are required for high-speed PLSKD. Here, we propose and demonstrate a unidirectional PLSKD scheme, where the channel reciprocity is reproduced by neural networks (NNs) so that highly correlated key waveforms are generated and shared between the legal users. Experimental results show that an error-free key generation rate (KGR) of 3.8 Gb/s with excellent randomness is achieved for an 11-km standard single-mode fiber (SSMF) channel. The proposed scheme alleviates the stringent requirement of bidirectional channel transmission in high-speed PLSKD and enables the integration of PLSKD and data transmission in the same fiber channel.

Optics Letters•Jul 20, 2022•17 citations

Distributed Physical Layer Key Generation Algorithm Based on Deep Learning

Wanting Geng, Li Sun, Qinghe Du

Physical layer encryption is an emerging security paradigm which supplements the higher-layer encryption solutions. To realize physical layer encryption, channel measurement is typically utilized as a randomness source to generate secret keys. Due to non-perfect reciprocity of the channels and the inevitable channel estimation errors resulting from noises and interferences, the channel measurements at the legitimate transceivers are not the same, yielding a mismatch in the generated keys. To address this issue, a distributed physical layer key generation scheme based on deep learning is proposed in this paper. A channel state information (CSI) learning neural network (CLNet) based on the autoencoder is deployed at both the transmitter and the receiver side to refine the initial channel estimation results. The CLNet takes the least square (LS) channel estimations as input and outputs the channel estimations more similar to the real channel. To train this CLNet, a channel equalization module together with a pre-trained maximum-likelihood (ML) detection network is deployed, which is used to make a decision on the transmitted pilot signal. Since the pilot is known as a priori, the cross entropy loss between the known pilot and the recovered one can be calculated, which implicitly indicates the accuracy of the refined CSI. Further, the weighted sum of the aforementioned cross entropy loss and the mean square loss between the original and the refined CSI estimates is utilized for training, which not only improves the CSI estimation quality but also avoids the over-fitting effect. Extensive simulation results show that compared with benchmark schemes, the proposed scheme improves the key agreement rate and the key generation rate at the legitimate users. Moreover, our method ensures a higher key disagreement rate between the legitimate user and the eavesdropper as well, especially in the low signal-to-noise ratio (SNR) regime.

IEEE Vehicular Technology Conference•Oct 10, 2023•3 citations

Channel characteristics estimation based on a secure optical transmission system with deep neural networks

Kun Wu, Hongxiang Wang, Yuefeng Ji

Optical transmission security has attracted much attention. In recent years, many secure optical transmission systems based on channel characteristics are proposed. However, there are many drawbacks with these systems, such as separated plaintext and key transmission, low key generation rate (KGR), insecurity when the eavesdropper has acquired the lengths of the local fibers utilized by legal parties. To solve the above problems, we propose a novel secure optical transmission system based on neural networks (NNs), which are employed to estimate channel characteristics. By training NNs locally and transmitting pseudo-keys, the proposed system can transmit the plaintext together with key, transforming the key dynamically. Moreover, since the channel characteristics for legal parties and eavesdropper are not completely identical, the NNs trained by legal parties and eavesdropper are inconsistent. Even though the eavesdropper has attained the lengths of local fibers wielded by legal parties, the NN model trained by the legal parties is still unavailable to illegal eavesdropper. The final key is generated by the trained NN and pseudo-key, so the keys generated by legal parties and eavesdropper are dissimilar. The simulation results prove the feasibility of the proposed system with the transmission distance of 100 km and the bit rate of 100 Gbps. Meanwhile, if plaintext and key have equivalent code length, the KGR of 50 Gbps for legal parties and the key disagreement rate (KDR) of 50% for illegal eavesdropper will be realized.

Optics Express•Aug 10, 2022•10 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.
The reciprocity of wireless channel between legitimate nodes is the premise of physical layer security key generation. Deep neural networks provide the non-linear transformation method to extract symmetric keys from reciprocal channel responses and show better freedom and performance than traditional methods. However, the hidden layer output in neural networks is unpredictable and the extracted high-dimensional features can not be estimated in advance, which is difficult to be applied to the key generation in the physical layer. In this paper, the key generation method based on WGAN-GP adversarial autoencoder is proposed to extract features efficiently between legitimate nodes, and the features can be fitted to the Gaussian distribution. Meanwhile, the Wasserstein distance and gradient penalty are applied in the game training to solve the gradient explosion. Compared with the PCA method, the proposed method has higher security key capacity, lower key error rate, and no interaction in the key generation process, which avoids key leakage.
Physical layer secure key distribution (PLSKD) in fiber networks provides high-level security originating from the channel uniqueness, while the channel reciprocity is shared between the legal users via bidirectional transmission. To ensure the key consistency, perfect wideband bidirectional optical devices are required for high-speed PLSKD. Here, we propose and demonstrate a unidirectional PLSKD scheme, where the channel reciprocity is reproduced by neural networks (NNs) so that highly correlated key waveforms are generated and shared between the legal users. Experimental results show that an error-free key generation rate (KGR) of 3.8 Gb/s with excellent randomness is achieved for an 11-km standard single-mode fiber (SSMF) channel. The proposed scheme alleviates the stringent requirement of bidirectional channel transmission in high-speed PLSKD and enables the integration of PLSKD and data transmission in the same fiber channel.
Physical layer encryption is an emerging security paradigm which supplements the higher-layer encryption solutions. To realize physical layer encryption, channel measurement is typically utilized as a randomness source to generate secret keys. Due to non-perfect reciprocity of the channels and the inevitable channel estimation errors resulting from noises and interferences, the channel measurements at the legitimate transceivers are not the same, yielding a mismatch in the generated keys. To address this issue, a distributed physical layer key generation scheme based on deep learning is proposed in this paper. A channel state information (CSI) learning neural network (CLNet) based on the autoencoder is deployed at both the transmitter and the receiver side to refine the initial channel estimation results. The CLNet takes the least square (LS) channel estimations as input and outputs the channel estimations more similar to the real channel. To train this CLNet, a channel equalization module together with a pre-trained maximum-likelihood (ML) detection network is deployed, which is used to make a decision on the transmitted pilot signal. Since the pilot is known as a priori, the cross entropy loss between the known pilot and the recovered one can be calculated, which implicitly indicates the accuracy of the refined CSI. Further, the weighted sum of the aforementioned cross entropy loss and the mean square loss between the original and the refined CSI estimates is utilized for training, which not only improves the CSI estimation quality but also avoids the over-fitting effect. Extensive simulation results show that compared with benchmark schemes, the proposed scheme improves the key agreement rate and the key generation rate at the legitimate users. Moreover, our method ensures a higher key disagreement rate between the legitimate user and the eavesdropper as well, especially in the low signal-to-noise ratio (SNR) regime.
Optical transmission security has attracted much attention. In recent years, many secure optical transmission systems based on channel characteristics are proposed. However, there are many drawbacks with these systems, such as separated plaintext and key transmission, low key generation rate (KGR), insecurity when the eavesdropper has acquired the lengths of the local fibers utilized by legal parties. To solve the above problems, we propose a novel secure optical transmission system based on neural networks (NNs), which are employed to estimate channel characteristics. By training NNs locally and transmitting pseudo-keys, the proposed system can transmit the plaintext together with key, transforming the key dynamically. Moreover, since the channel characteristics for legal parties and eavesdropper are not completely identical, the NNs trained by legal parties and eavesdropper are inconsistent. Even though the eavesdropper has attained the lengths of local fibers wielded by legal parties, the NN model trained by the legal parties is still unavailable to illegal eavesdropper. The final key is generated by the trained NN and pseudo-key, so the keys generated by legal parties and eavesdropper are dissimilar. The simulation results prove the feasibility of the proposed system with the transmission distance of 100 km and the bit rate of 100 Gbps. Meanwhile, if plaintext and key have equivalent code length, the KGR of 50 Gbps for legal parties and the key disagreement rate (KDR) of 50% for illegal eavesdropper will be realized.