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

arXiv:2105.08364 · IEEE Internet of Things Journal

Deep-Learning-Based Physical-Layer Secret Key Generation for FDD Systems

Xinwei Zhang, Guyue Li, Junqing Zhang, Aiqun Hu, Zongyue Hou, Bin Xiao

Published Sep 1, 2021• 98 citations
arXivHTMLPDF

Abstract

Physical-layer key generation (PKG) establishes cryptographic keys from highly correlated measurements of wireless channels, which relies on reciprocal channel characteristics between uplink and downlink, is a promising wireless security technique for Internet of Things (IoT). However, it is challenging to extract common features in frequency-division duplexing (FDD) systems as uplink and downlink transmissions operate at different frequency bands whose channel frequency responses are not reciprocal anymore. Existing PKG methods for FDD systems have many limitations, i.e., high overhead and security problems. This article proposes a novel PKG scheme that uses the feature mapping function between different frequency bands obtained by deep learning to make two users generate highly similar channel features in FDD systems. In particular, this is the first time to apply deep learning for PKG in FDD systems. We first prove the existence of the band feature mapping function for a given environment and a feedforward network with a single hidden layer can approximate the mapping function. Then, a key generation neural network (KGNet) is proposed for reciprocal channel feature construction, and a key generation scheme based on the KGNet is also proposed. Numerical results verify the excellent performance of the KGNet-based key generation scheme in terms of randomness, key generation ratio, and key error rate. Besides, the overhead analysis shows that the method proposed in this article can be used for resource-constrained IoT devices in FDD systems.

DOI
10.1109/jiot.2021.3109272

Related papers

Exploiting FDD Channel Reciprocity for Physical Layer Secret Key Generation in IoT Networks

Ehsan Olyaei Torshizi, Werner Henkel

The utilization of physical layer Secret Key Generation (SKG) is increasingly prevalent in securing wireless communication within Internet of Things systems, particularly in Narrow-band IoT. While most key-generation schemes are tailored for Time Division Duplex (TDD) systems, generating secret keys in Frequency Division Duplex (FDD) systems presents challenges due to the distinct frequency bands for uplink and downlink. In response to this, we propose an efficient FDD-based key generation technique that capitalizes on the reciprocity of scattering matrix parametersS12andS21within the same frequency range. Specifically, we harness the capabilities of MUSIC algorithm during the direction of arrival estimation phase. Numerical results demonstrate promising outcomes in addressing key challenges, including randomness, and Key Disagreement Ratio (KDR).

IEEE Communications Letters•Apr 12, 2024•23 citations

Pairwise Physical Layer Secret Key Generation for FDD Systems

Ehsan Olyaei Torshizi, Werner Henkel

Physical-layer secret key generation (PSKG) stands as a promising privacy protection technique, establishing shared encryption keys through the analysis of highly correlated wireless channel measurements. This approach relies on exploiting reciprocal channel characteristics between uplink and downlink transmissions. Nonetheless, the distinct carrier frequencies employed for uplink and downlink in frequency-division duplexing (FDD) systems pose a challenge in identifying common features. This paper presents a novel approach that exploits the inherent reciprocity between scattering parameters of passive two-port networks within same frequency ranges to overcome this obstacle. By capitalizing this reciprocity and considering closely situated FDD bands, a seamless continuity is anticipated in phase differences extracted form the corresponding S-parameters, between neighboring antennas of an antenna array from both uplink and downlink directions. This continuity, thereby ensures consistency in the generated keys from both transmission ends. Furthermore, a two-stage pre-processing method is proposed to enhance performance effectively. Additionally, the paper suggests the utilization of polynomial curve-fitting through measurement data to improve reciprocity and proposes a non-linear framework for quantizing the merging points of the two FDD bands. A statistical analysis employing multiple linear regression is provided to determine the error probability associated with the generated keys. Empirical results validate the feasibility and effectiveness of the proposed key generation scheme, affirming its attributes in terms of randomness, efficiency, key distribution uniformity, and key disagreement ratio (KDR).

IEEE Transactions on Information Forensics and Security•Jan 1, 2024•13 citations

Channel Feature Extraction and Physical Layer Key Generation in FDD Massive MIMO Systems

Xinzhu Hu

While Physical Layer Key Generation (PKG) offers lightweight security for 6G IoT, channel non-reciprocity in FDD massive MIMO degrades key consistency. This paper presents a comprehensive review of Physical Layer Key Generation (PKG) techniques within Frequency Division Duplex (FDD) massive MIMO systems. While PKG leverages the inherent randomness of wireless channels to establish lightweight security for communication nodes, FDD systems pose a significant challenge. The separated uplink and downlink bands produce non-reciprocal fast-fading channel responses, which inherently degrade the consistency of keys generated from instantaneous channel state information (CSI). To address this, this study categorizes existing methodologies into three primary routes: stable propagation feature extraction, intelligent feature mapping, and system engineering optimization. It examines their mechanisms across the angle, beam, and statistical covariance domains, comparing representative schemes in terms of Key Disagreement Rate (KDR), overhead, and computational complexity. Ultimately, future research must integrate physical priors with data-driven models to ensure robust security in practical 6G networks.

ITM Web of Conferences•Jan 1, 2026•0 citations

CSI-Driven Physical Layer Secret Key Generation for FDD Systems

Ehsan Olyaei Torshizi, Anas Alashqar, Werner Henkel

Physical Layer Secret Key Generation (PLSKG), which utilizes wireless channel reciprocity, is increasingly adopted to secure wireless communications. In Time Division Duplexing (TDD) systems, the inherent channel reciprocity facilitates the generation of cryptographic keys without requiring a key exchange process. Conversely, Frequency Division Duplexing (FDD) systems present greater challenges for key generation due to the use of distinct frequency bands for uplink and downlink, resulting in differing frequency responses. In this paper, we address this challenge by modeling the channel along with connecting cables as a two-port network and utilizing the reciprocity principles applicable to such networks within the same frequency range. For key generation, we construct the channel profile for each FDD band by utilizing the amplitude of the bidirectional scattering parameters S12and S21in two closely spaced FDD bands, thereby ensuring the required reciprocity in FDD systems. To assess the practicality of the proposed scheme, we analyze its performance across various indoor scenarios and compare it with other key generation schemes using multiple performance indicators. The comparative results confirm the feasibility and effectiveness of our scheme in terms of randomness and key disagreement ratio.

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)•Sep 1, 2025•0 citations

Enabling Deep Learning-Based Physical-Layer Secret Key Generation for FDD-OFDM Systems in Multi-Environments

Xinwei Zhang, Guyue Li, Junqing Zhang +3 more

Deep learning-based physical-layer secret key generation (PKG) has been used to overcome the imperfect uplink/downlink channel reciprocity in frequency division duplexing (FDD) orthogonal frequency division multiplexing (OFDM) systems. However, existing efforts have focused on key generation for users in a specific environment where the training samples and test samples follow the same distribution, which is unrealistic for real-world applications. This paper formulates the PKG problem in multiple environments as a learning-based problem by learning the knowledge such as data and models from known environments to generate keys quickly and efficiently in multiple new environments. Specifically, we propose deep transfer learning (DTL) and meta-learning-based channel feature mapping algorithms for key generation. The two algorithms use different training methods to pre-train the model in the known environments, and then quickly adapt and deploy the model to new environments. Simulation and experimental results show that compared with the methods without adaptation, the DTL and meta-learning algorithms both can improve the performance of generated keys. In addition, the complexity analysis shows that the meta-learning algorithm can achieve better performance than the DTL algorithm with less cost.

arXiv:2211.03065•IEEE Transactions on Vehicular Technology•Feb 20, 2024•28 citations

Secret Key Generation Scheme Based on Generative Adversarial Networks in FDD Systems

Zongyue Hou, Xinwei Zhang

In frequency division duplexing (FDD) systems, the uplink and downlink transmit information in different frequency bands, so it is difficult to use channel reciprocity to generate secret keys. Existing key generation methods for FDD systems have excessive overhead and security problems. This paper uses deep learning to predict the downlink channel state information (CSI) from the uplink CSI, so that two users can generate highly similar downlink CSI in FDD systems. We propose a key generation scheme based on boundary equilibrium generative adversarial network (BEGAN), including channel estimation, reciprocal channel feature construction, quantization, information reconciliation and privacy amplification. Numerical simulation results are presented to verify the feasibility and effectiveness of the proposed scheme.

IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)•May 10, 2021•9 citations
Physical-layer key generation (PKG) establishes cryptographic keys from highly correlated measurements of wireless channels, which relies on reciprocal channel characteristics between uplink and downlink, is a promising wireless security technique for Internet of Things (IoT). However, it is challenging to extract common features in frequency-division duplexing (FDD) systems as uplink and downlink transmissions operate at different frequency bands whose channel frequency responses are not reciprocal anymore. Existing PKG methods for FDD systems have many limitations, i.e., high overhead and security problems. This article proposes a novel PKG scheme that uses the feature mapping function between different frequency bands obtained by deep learning to make two users generate highly similar channel features in FDD systems. In particular, this is the first time to apply deep learning for PKG in FDD systems. We first prove the existence of the band feature mapping function for a given environment and a feedforward network with a single hidden layer can approximate the mapping function. Then, a key generation neural network (KGNet) is proposed for reciprocal channel feature construction, and a key generation scheme based on the KGNet is also proposed. Numerical results verify the excellent performance of the KGNet-based key generation scheme in terms of randomness, key generation ratio, and key error rate. Besides, the overhead analysis shows that the method proposed in this article can be used for resource-constrained IoT devices in FDD systems.
The utilization of physical layer Secret Key Generation (SKG) is increasingly prevalent in securing wireless communication within Internet of Things systems, particularly in Narrow-band IoT. While most key-generation schemes are tailored for Time Division Duplex (TDD) systems, generating secret keys in Frequency Division Duplex (FDD) systems presents challenges due to the distinct frequency bands for uplink and downlink. In response to this, we propose an efficient FDD-based key generation technique that capitalizes on the reciprocity of scattering matrix parametersS12andS21within the same frequency range. Specifically, we harness the capabilities of MUSIC algorithm during the direction of arrival estimation phase. Numerical results demonstrate promising outcomes in addressing key challenges, including randomness, and Key Disagreement Ratio (KDR).
Physical-layer secret key generation (PSKG) stands as a promising privacy protection technique, establishing shared encryption keys through the analysis of highly correlated wireless channel measurements. This approach relies on exploiting reciprocal channel characteristics between uplink and downlink transmissions. Nonetheless, the distinct carrier frequencies employed for uplink and downlink in frequency-division duplexing (FDD) systems pose a challenge in identifying common features. This paper presents a novel approach that exploits the inherent reciprocity between scattering parameters of passive two-port networks within same frequency ranges to overcome this obstacle. By capitalizing this reciprocity and considering closely situated FDD bands, a seamless continuity is anticipated in phase differences extracted form the corresponding S-parameters, between neighboring antennas of an antenna array from both uplink and downlink directions. This continuity, thereby ensures consistency in the generated keys from both transmission ends. Furthermore, a two-stage pre-processing method is proposed to enhance performance effectively. Additionally, the paper suggests the utilization of polynomial curve-fitting through measurement data to improve reciprocity and proposes a non-linear framework for quantizing the merging points of the two FDD bands. A statistical analysis employing multiple linear regression is provided to determine the error probability associated with the generated keys. Empirical results validate the feasibility and effectiveness of the proposed key generation scheme, affirming its attributes in terms of randomness, efficiency, key distribution uniformity, and key disagreement ratio (KDR).
While Physical Layer Key Generation (PKG) offers lightweight security for 6G IoT, channel non-reciprocity in FDD massive MIMO degrades key consistency. This paper presents a comprehensive review of Physical Layer Key Generation (PKG) techniques within Frequency Division Duplex (FDD) massive MIMO systems. While PKG leverages the inherent randomness of wireless channels to establish lightweight security for communication nodes, FDD systems pose a significant challenge. The separated uplink and downlink bands produce non-reciprocal fast-fading channel responses, which inherently degrade the consistency of keys generated from instantaneous channel state information (CSI). To address this, this study categorizes existing methodologies into three primary routes: stable propagation feature extraction, intelligent feature mapping, and system engineering optimization. It examines their mechanisms across the angle, beam, and statistical covariance domains, comparing representative schemes in terms of Key Disagreement Rate (KDR), overhead, and computational complexity. Ultimately, future research must integrate physical priors with data-driven models to ensure robust security in practical 6G networks.
Physical Layer Secret Key Generation (PLSKG), which utilizes wireless channel reciprocity, is increasingly adopted to secure wireless communications. In Time Division Duplexing (TDD) systems, the inherent channel reciprocity facilitates the generation of cryptographic keys without requiring a key exchange process. Conversely, Frequency Division Duplexing (FDD) systems present greater challenges for key generation due to the use of distinct frequency bands for uplink and downlink, resulting in differing frequency responses. In this paper, we address this challenge by modeling the channel along with connecting cables as a two-port network and utilizing the reciprocity principles applicable to such networks within the same frequency range. For key generation, we construct the channel profile for each FDD band by utilizing the amplitude of the bidirectional scattering parameters S12and S21in two closely spaced FDD bands, thereby ensuring the required reciprocity in FDD systems. To assess the practicality of the proposed scheme, we analyze its performance across various indoor scenarios and compare it with other key generation schemes using multiple performance indicators. The comparative results confirm the feasibility and effectiveness of our scheme in terms of randomness and key disagreement ratio.
Deep learning-based physical-layer secret key generation (PKG) has been used to overcome the imperfect uplink/downlink channel reciprocity in frequency division duplexing (FDD) orthogonal frequency division multiplexing (OFDM) systems. However, existing efforts have focused on key generation for users in a specific environment where the training samples and test samples follow the same distribution, which is unrealistic for real-world applications. This paper formulates the PKG problem in multiple environments as a learning-based problem by learning the knowledge such as data and models from known environments to generate keys quickly and efficiently in multiple new environments. Specifically, we propose deep transfer learning (DTL) and meta-learning-based channel feature mapping algorithms for key generation. The two algorithms use different training methods to pre-train the model in the known environments, and then quickly adapt and deploy the model to new environments. Simulation and experimental results show that compared with the methods without adaptation, the DTL and meta-learning algorithms both can improve the performance of generated keys. In addition, the complexity analysis shows that the meta-learning algorithm can achieve better performance than the DTL algorithm with less cost.
In frequency division duplexing (FDD) systems, the uplink and downlink transmit information in different frequency bands, so it is difficult to use channel reciprocity to generate secret keys. Existing key generation methods for FDD systems have excessive overhead and security problems. This paper uses deep learning to predict the downlink channel state information (CSI) from the uplink CSI, so that two users can generate highly similar downlink CSI in FDD systems. We propose a key generation scheme based on boundary equilibrium generative adversarial network (BEGAN), including channel estimation, reciprocal channel feature construction, quantization, information reconciliation and privacy amplification. Numerical simulation results are presented to verify the feasibility and effectiveness of the proposed scheme.